INDEX

Explanations

terms related to threats, risks, and dangers

oai_token-act-pair · gpt-3.5-turbo

words associated with various types of threats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ricks

-0.83

urses

-0.83

arist

-0.77

 gown

-0.69

urgy

-0.67

otide

-0.66

tein

-0.66

gian

-0.66

coat

-0.66

 Band

-0.66

POSITIVE LOGITS

 posed

1.25

 threat

0.99

 threats

0.96

threat

0.89

 Threat

0.82

crow

0.81

 emanating

0.78

xual

0.78

lessly

0.76

 glare

0.74

Activations Density 0.055%

terms related to threats, risks, and dangers

words associated with various types of threats

No Comments

No Known Activations