INDEX

Explanations

words related to security breaches or violations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "breach" and related terminology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 redistributed

-0.81

atable

-0.73

 Towns

-0.68

minist

-0.64

ohyd

-0.63

 Glob

-0.61

ENTS

-0.61

 Hungry

-0.60

NAS

-0.60

uana

-0.59

POSITIVE LOGITS

 breach

1.24

 breaches

1.18

 breached

0.97

 breaching

0.88

 Breach

0.87

ionage

0.84

breakers

0.75

hole

0.75

ingly

0.73

aucus

0.73

Activations Density 0.007%

words related to security breaches or violations

occurrences of the word "breach" and related terminology

No Comments

No Known Activations