INDEX

Explanations

user identifiers or tags

oai_token-act-pair · gpt-3.5-turbo

usernames or handles typically seen in social media 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

wcsstore

-0.73

 beginners

-0.64

values

-0.64

 coord

-0.63

Collins

-0.62

CLASSIFIED

-0.62

 scrut

-0.62

benefit

-0.60

Lens

-0.58

 fundament

-0.58

POSITIVE LOGITS

qq

0.85

ihara

0.82

jri

0.79

tsky

0.78

ua

0.75

zb

0.74

jj

0.74

_-

0.74

uj

0.72

Uk

0.71

Activations Density 0.070%

user identifiers or tags

usernames or handles typically seen in social media contexts

No Comments

No Known Activations