INDEX

Explanations

personal pronouns and possessive pronouns referring to individuals or groups

oai_token-act-pair · gpt-3.5-turbo

references to personal pronouns or mentions of individuals

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

earch

-0.57

arsity

-0.55

atlantic

-0.51

 Eleven

-0.50

idth

-0.48

noon

-0.48

inton

-0.48

 Gulf

-0.47

 Amin

-0.44

CCC

-0.44

POSITIVE LOGITS

'll

0.84

've

0.83

'd

0.81

're

0.78

self

0.75

own

0.75

 knew

0.61

selves

0.61

can

0.58

 cannot

0.58

Activations Density 0.958%

personal pronouns and possessive pronouns referring to individuals or groups

references to personal pronouns or mentions of individuals

No Comments

No Known Activations