INDEX

Explanations

instances of words related to public statements or actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "publicly."

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

nesota

-0.90

nian

-0.76

tein

-0.72

illas

-0.71

ĸļ

-0.71

ailand

-0.70

 Salvador

-0.70

anwhile

-0.69

 Stick

-0.69

akeru

-0.69

POSITIVE LOGITS

 humiliated

0.80

 traded

0.80

ached

0.78

 speaking

0.76

ised

0.73

isSpecialOrderable

0.73

licted

0.72

 addressed

0.71

 dispersed

0.71

 pronounce

0.70

Activations Density 0.010%

instances of words related to public statements or actions

instances of the word "publicly."

No Comments

No Known Activations