INDEX

Explanations

phrases related to legal or regulatory actions

oai_token-act-pair · gpt-3.5-turbo

terms related to legislative processes and actions

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

 Sandra

-0.68

olulu

-0.66

 celeb

-0.64

 bikini

-0.63

perse

-0.61

robe

-0.60

affe

-0.59

iverse

-0.59

 nutshell

-0.59

gettable

-0.59

POSITIVE LOGITS

 thereof

0.85

ptive

0.83

ptions

0.83

eering

0.80

Reviewer

0.79

illation

0.78

ism

0.76

 Techniques

0.73

 Mechan

0.73

of

0.72

Activations Density 0.281%

phrases related to legal or regulatory actions

terms related to legislative processes and actions

No Comments

No Known Activations