INDEX

Explanations

adjectives or nouns related to harmful or risky situations

oai_token-act-pair · gpt-3.5-turbo

terms that indicate a sense of danger or harmfulness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

arest

-0.81

Ħ¢

-0.78

olitan

-0.77

orthy

-0.75

edia

-0.75

ļéĨĴ

-0.75

ī

-0.75

apolis

-0.73

elle

-0.72

gdala

-0.72

POSITIVE LOGITS

 combination

0.91

 combinations

0.78

 stunts

0.78

 dangerous

0.78

 endanger

0.77

 snakes

0.77

 situations

0.77

 slope

0.76

 adolesc

0.74

ening

0.74

Activations Density 0.056%

adjectives or nouns related to harmful or risky situations

terms that indicate a sense of danger or harmfulness

No Comments

No Known Activations