INDEX

Explanations

sentences where the phrase "one thing that" is used to introduce a main point or observation

oai_token-act-pair · gpt-3.5-turbo

phrases beginning with "one thing that" or similar constructions indicating a specific point or observation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arus

-0.78

unctions

-0.70

uci

-0.69

eps

-0.68

zzy

-0.66

renheit

-0.65

osph

-0.64

liv

-0.64

ceans

-0.64

blast

-0.64

POSITIVE LOGITS

 distinguishing

0.72

\":

0.66

 determining

0.66

 strang

0.66

 excludes

0.65

 downside

0.64

 difference

0.63

 common

0.62

 interest

0.62

uman

0.61

Activations Density 0.291%

sentences where the phrase "one thing that" is used to introduce a main point or observation

phrases beginning with "one thing that" or similar constructions indicating a specific point or observation

No Comments

No Known Activations