INDEX

Explanations

phrases introducing speculations or claims

oai_token-act-pair · gpt-3.5-turbo

the word "that" being used in various contexts

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

aukee

-0.71

Lex

-0.66

PokÃ©

-0.65

izont

-0.65

Luck

-0.61

MX

-0.61

ãĤ´ãĥ³

-0.60

erenn

-0.60

 stall

-0.59

PRESS

-0.58

POSITIVE LOGITS

 consequently

0.84

 culminated

0.81

soever

0.77

 furthermore

0.74

 resulted

0.72

 moreover

0.71

milo

0.70

 reconc

0.68

cher

0.68

 secondly

0.68

Activations Density 0.146%

phrases introducing speculations or claims

the word "that" being used in various contexts

No Comments

No Known Activations