INDEX

Explanations

legislation or measures that have been officially approved or voted on

oai_token-act-pair · gpt-3.5-turbo

words related to legislative approvals and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Pic

-0.71

é¾įåĸļå£«

-0.70

PLIED

-0.69

cture

-0.68

LP

-0.67

hide

-0.67

inos

-0.64

img

-0.63

sing

-0.62

EMOTE

-0.61

POSITIVE LOGITS

 unanimously

0.97

 stricter

0.83

 harsher

0.79

 amendments

0.77

 sweeping

0.77

 legislation

0.76

 legalizing

0.72

 postpone

0.71

 reforms

0.69

 authorizing

0.69

Activations Density 0.251%

legislation or measures that have been officially approved or voted on

words related to legislative approvals and decisions

No Comments

No Known Activations