INDEX

Explanations

terms related to prohibitions and restrictions

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

terms related to prohibition or restriction, often in a legal context

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lycer

-0.83

oÄŁ

-0.75

Lenin

-0.72

quickShipAvailable

-0.70

swick

-0.69

ammy

-0.69

sie

-0.65

yssey

-0.65

estate

-0.65

VERTISEMENT

-0.65

POSITIVE LOGITS

 anyone

0.98

 anybody

0.89

 smoking

0.85

 unnecessary

0.81

 gambling

0.79

 offending

0.79

 excessive

0.77

enance

0.77

 disbelief

0.77

 importing

0.76

Activations Density 0.072%

terms related to prohibitions and restrictions

terms related to prohibition or restriction, often in a legal context

No Comments

No Known Activations