INDEX

Explanations

email addresses or URLs

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and their frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

etooth

-0.78

 tremend

-0.78

ĸļ

-0.73

igue

-0.71

yan

-0.70

 trouble

-0.66

ivable

-0.66

gomery

-0.65

undai

-0.65

ema

-0.64

POSITIVE LOGITS

 Provided

0.86

YES

0.81

 http

0.80

 âĢİ

0.79

 https

0.78

CV

0.78

 Logged

0.77

Allows

0.76

 âĨĳ

0.75

0.74

Activations Density 0.131%

email addresses or URLs

punctuation marks and their frequency

No Comments

No Known Activations