INDEX

Explanations

phrases indicating requests or invitations

oai_token-act-pair · gpt-3.5-turbo

references to individuals and their interactions or requests in narratives

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

 Siege

-0.65

 Fried

-0.63

inf

-0.63

ionic

-0.62

isite

-0.60

 Ange

-0.60

 Execution

-0.59

apter

-0.59

 Athe

-0.59

 Firefly

-0.58

POSITIVE LOGITS

 orally

0.89

 privately

0.70

 withd

0.68

 verbally

0.68

 downstairs

0.68

 personally

0.67

 harshly

0.66

 backstage

0.65

dur

0.65

 angrily

0.63

Activations Density 0.176%

phrases indicating requests or invitations

references to individuals and their interactions or requests in narratives

No Comments

No Known Activations