INDEX

Explanations

mentions of protection-related terms

oai_token-act-pair · gpt-3.5-turbo

references to concepts of protection or safeguarding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

mers

-0.70

eton

-0.67

bold

-0.66

nexus

-0.64

 Kinn

-0.62

sonian

-0.61

LINE

-0.61

leaf

-0.60

hler

-0.60

 PRESIDENT

-0.59

POSITIVE LOGITS

ively

1.02

iveness

1.01

 afforded

0.95

 against

0.92

ously

0.92

against

0.81

ective

0.80

aments

0.79

ament

0.79

orate

0.78

Activations Density 0.064%

mentions of protection-related terms

references to concepts of protection or safeguarding

No Comments

No Known Activations