INDEX

Explanations

phrases expressing uncertainty or lack of knowledge

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing uncertainty or inevitability

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

 antioxid

-0.74

 SetTextColor

-0.70

esm

-0.66

 portfolios

-0.62

yip

-0.62

 Literary

-0.59

hai

-0.59

redients

-0.59

 some

-0.58

 Crusader

-0.57

POSITIVE LOGITS

nor

0.93

theless

0.92

 dime

0.90

rences

0.79

 bothered

0.77

 EVER

0.77

 anymore

0.74

Initialized

0.74

 slightest

0.71

 dreamed

0.70

Activations Density 0.107%

phrases expressing uncertainty or lack of knowledge

phrases emphasizing uncertainty or inevitability

No Comments

No Known Activations