INDEX

Explanations

proper nouns, particularly character names in movies or books

oai_token-act-pair · gpt-3.5-turbo

the presence of parentheses and their occurrences in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 retard

-0.81

 entitle

-0.76

 increment

-0.71

 nuts

-0.70

 expiration

-0.70

 depress

-0.69

 intensive

-0.69

 overlap

-0.68

nut

-0.68

 afford

-0.68

POSITIVE LOGITS

sic

1.56

aka

1.53

formerly

1.50

pictured

1.44

whose

1.28

which

1.27

?)

1.27

?),

1.23

see

1.23

pron

1.23

Activations Density 0.170%

proper nouns, particularly character names in movies or books

the presence of parentheses and their occurrences in the text

No Comments

No Known Activations