INDEX

Explanations

references to privacy policies

oai_token-act-pair · gpt-3.5-turbo

terms related to privacy and policy agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nces

-0.91

ingly

-0.85

enegger

-0.82

 Flavoring

-0.82

htaking

-0.81

ITNESS

-0.79

NetMessage

-0.76

å¥³

-0.75

eneg

-0.74

issance

-0.69

POSITIVE LOGITS

 prohibiting

0.89

 enforced

0.89

 Enforcement

0.89

 enforcement

0.85

 abiding

0.84

 violation

0.76

 governing

0.76

 Directive

0.75

 restricting

0.74

 booklet

0.74

Activations Density 0.036%

references to privacy policies

terms related to privacy and policy agreements

No Comments

No Known Activations