INDEX

Explanations

words related to vulnerabilities or weaknesses

oai_token-act-pair · gpt-3.5-turbo

terms related to weaknesses

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

agher

-0.90

rea

-0.84

ahon

-0.77

iser

-0.72

aston

-0.71

yton

-0.69

ilon

-0.69

ateur

-0.69

ICA

-0.68

eer

-0.67

POSITIVE LOGITS

 weakness

0.97

 aversion

0.89

 Weak

0.87

 weaknesses

0.86

 limitation

0.82

Weak

0.80

 susceptibility

0.75

 weaken

0.71

 vulner

0.70

 tolerance

0.69

Activations Density 0.021%

words related to vulnerabilities or weaknesses

terms related to weaknesses

No Comments

No Known Activations