INDEX

Explanations

words related to vulnerabilities or weaknesses

oai_token-act-pair · gpt-3.5-turbo

mentions of weakness and vulnerabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rea

-0.93

agher

-0.87

ateur

-0.74

orate

-0.72

aston

-0.72

arel

-0.71

rolley

-0.68

cise

-0.67

alogue

-0.65

ahon

-0.65

POSITIVE LOGITS

 weakness

1.09

 weaknesses

0.92

 aversion

0.85

 Weak

0.83

nesses

0.82

 undermin

0.82

 limitation

0.79

Weak

0.78

 weak

0.77

 tolerance

0.76

Activations Density 0.008%

words related to vulnerabilities or weaknesses

mentions of weakness and vulnerabilities

No Comments

No Known Activations