INDEX

Explanations

quotations with spoken words

oai_token-act-pair · gpt-3.5-turbo

reported speech or quotations

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

 treaties

-0.72

-0.71

 allied

-0.69

etheless

-0.68

recomm

-0.68

idelines

-0.68

 unified

-0.66

 enshr

-0.66

rats

-0.66

 throne

-0.65

POSITIVE LOGITS

 remembers

0.94

 recalls

0.83

 chuck

0.77

 recalling

0.77

 Vaugh

0.75

 reminis

0.72

 Grow

0.72

 Growing

0.70

ewitness

0.70

 laughs

0.70

Activations Density 0.404%

quotations with spoken words

reported speech or quotations

No Comments

No Known Activations