INDEX

Explanations

specific strings of characters that likely indicate a pattern or code

oai_token-act-pair · gpt-3.5-turbo

variations of the word "lie" and related expressions

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

Negative Logits

omorphic

-0.71

 Alban

-0.67

 Gmail

-0.67

 civilian

-0.65

 Skydragon

-0.63

è¦ļéĨĴ

-0.59

Kaf

-0.57

oun

-0.57

 Alph

-0.56

 Tucson

-0.56

POSITIVE LOGITS

lights

0.74

ski

0.73

else

0.73

0.70

tu

0.70

mean

0.69

sure

0.69

own

0.69

mand

0.66

thy

0.66

Activations Density 0.288%

specific strings of characters that likely indicate a pattern or code

variations of the word "lie" and related expressions

No Known Activations