INDEX

Explanations

mentions of policies and guidelines

oai_token-act-pair · gpt-3.5-turbo

references to policies, particularly in formal 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ITNESS

-0.80

nces

-0.78

ingly

-0.75

 Flavoring

-0.72

ymes

-0.71

 Stain

-0.70

Ago

-0.69

burn

-0.69

semble

-0.67

htaking

-0.66

POSITIVE LOGITS

 prohibiting

0.93

 enforcement

0.92

holders

0.91

 makers

0.90

 Enforcement

0.87

 restricting

0.81

holder

0.81

 abiding

0.80

making

0.78

enforcement

0.77

Activations Density 0.032%

mentions of policies and guidelines

references to policies, particularly in formal contexts

No Comments

No Known Activations