INDEX

Explanations

phrases and terms related to strategies and actions aimed at preventing various issues or conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to prevention and protective measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 monop

-0.89

ithing

-0.73

doms

-0.71

 transcripts

-0.67

ammy

-0.66

 Doodle

-0.65

 gobl

-0.64

 Syndicate

-0.64

lycer

-0.63

Nib

-0.62

POSITIVE LOGITS

ative

0.80

ist

0.76

 vacc

0.74

ista

0.74

 prevention

0.72

avior

0.72

etheless

0.68

ohydrate

0.68

ãĥŁ

0.67

escal

0.66

Activations Density 0.077%

phrases and terms related to strategies and actions aimed at preventing various issues or conditions

terms related to prevention and protective measures

No Comments

No Known Activations