INDEX

Explanations

mentions of specific titles, particularly related to movies and shows

oai_token-act-pair · gpt-3.5-turbo

proper nouns and titles related to various forms of media and personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 themselves

-0.86

 Himself

-0.77

 himself

-0.70

 yourselves

-0.70

 headquartered

-0.65

ributes

-0.64

Their

-0.63

 prominently

-0.63

arnaev

-0.60

idates

-0.60

POSITIVE LOGITS

 colleague

1.10

 myself

0.96

husband

0.93

 friends

0.93

 roommate

0.92

 friend

0.90

 buddies

0.89

favorite

0.89

 girlfriend

0.88

 buddy

0.88

Activations Density 0.300%

mentions of specific titles, particularly related to movies and shows

proper nouns and titles related to various forms of media and personal experiences

No Comments

No Known Activations