INDEX

Explanations

words related to security breaches

oai_token-act-pair · gpt-3.5-turbo

mentions of breaches or violations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

uana

-0.88

 redistributed

-0.68

lee

-0.67

zl

-0.67

 stag

-0.65

minist

-0.65

ICA

-0.64

onga

-0.63

 livest

-0.63

opped

-0.63

POSITIVE LOGITS

 breaches

0.88

terness

0.81

 breach

0.80

ingly

0.77

hold

0.76

hole

0.73

 Breach

0.72

aucus

0.72

holes

0.70

ware

0.70

Activations Density 0.032%

words related to security breaches

mentions of breaches or violations

No Comments

No Known Activations