INDEX

Explanations

suggestions or recommendations

oai_token-act-pair · gpt-3.5-turbo

recommendations or suggestions given in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mehran

-0.70

agos

-0.69

ELD

-0.66

Ern

-0.66

anty

-0.65

PRESS

-0.63

isol

-0.59

 Beast

-0.57

Ship

-0.57

FN

-0.57

POSITIVE LOGITS

 reconsider

0.99

ħĭ

0.86

iquette

0.81

 rethink

0.80

 recommendation

0.78

 proceed

0.75

 caution

0.74

 adopt

0.74

 remedy

0.73

 ditch

0.72

Activations Density 0.233%

suggestions or recommendations

recommendations or suggestions given in various contexts

No Comments

No Known Activations