INDEX

Explanations

references to privacy policies and terms of use

oai_token-act-pair · gpt-3.5-turbo

terms related to privacy policies and data protection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

×Ļ×

-0.86

jin

-0.76

unes

-0.74

ppo

-0.72

à¤

-0.71

jp

-0.70

stals

-0.69

á

-0.69

amins

-0.67

×Ļ

-0.67

POSITIVE LOGITS

 Privacy

1.11

 privacy

0.93

 Seym

0.84

 Preferences

0.81

ocene

0.80

 behavi

0.79

 Rights

0.79

Privacy

0.73

 coerc

0.72

ographically

0.71

Activations Density 0.009%

references to privacy policies and terms of use

terms related to privacy policies and data protection

No Comments

No Known Activations