INDEX

Explanations

proper nouns related to various individuals and entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and organizations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Burg

-0.63

Tes

-0.60

cientious

-0.58

 lett

-0.58

 chronological

-0.58

 understatement

-0.56

piring

-0.55

NRL

-0.55

 Corpus

-0.55

 adolesc

-0.53

POSITIVE LOGITS

 specializes

0.84

 reportedly

0.82

 testified

0.78

 died

0.77

 apologized

0.77

rite

0.76

 consisted

0.76

's

0.74

enegger

0.73

was

0.73

Activations Density 0.422%

proper nouns related to various individuals and entities

proper nouns, particularly names of individuals and organizations

No Comments

No Known Activations