INDEX

Explanations

mentions of actions taken involving victims

oai_token-act-pair · gpt-3.5-turbo

references to victims and their treatment 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

é¾įå¥ĳå£«

-0.80

 Built

-0.72

 Lessons

-0.70

è¦ļéĨĴ

-0.70

 Critics

-0.69

 externalToEVAOnly

-0.65

Northern

-0.64

antle

-0.63

equality

-0.63

 Ranked

-0.62

POSITIVE LOGITS

 herself

0.83

 himself

0.80

 whom

0.80

 remorse

0.74

 identifiable

0.72

 immedi

0.71

 identified

0.70

ENT

0.69

 narr

0.67

doctor

0.67

Activations Density 0.615%

mentions of actions taken involving victims

references to victims and their treatment in narratives

No Comments

No Known Activations