INDEX

Explanations

words related to safety and security

oai_token-act-pair · gpt-3.5-turbo

references to safety and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

essee

-0.87

hun

-0.86

ette

-0.85

fred

-0.80

frey

-0.79

ional

-0.77

anche

-0.76

hr

-0.75

eb

-0.74

hoff

-0.74

POSITIVE LOGITS

 than

1.10

 safer

0.82

 alternatives

0.78

 Than

0.77

 behaved

0.75

 precaution

0.75

 safe

0.73

 redes

0.71

 sounding

0.71

 isot

0.71

Activations Density 0.012%

words related to safety and security

references to safety and security

No Comments

No Known Activations