INDEX

Explanations

phrases or sentences indicating that no information or comments are provided on a specific topic

oai_token-act-pair · gpt-3.5-turbo

instances of phrases that indicate a lack of comment or response

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

reference

-0.89

YE

-0.83

YP

-0.77

externalActionCode

-0.74

SourceFile

-0.74

©¶æ¥µ

-0.73

MAP

-0.72

NK

-0.71

ARM

-0.71

Reference

-0.71

POSITIVE LOGITS

 behalf

1.55

erous

1.13

shore

0.95

slaught

0.84

 occasion

0.83

etime

0.80

eness

0.80

 topics

0.79

etimes

0.78

how

0.78

Activations Density 0.133%

phrases or sentences indicating that no information or comments are provided on a specific topic

instances of phrases that indicate a lack of comment or response

No Comments

No Known Activations