INDEX

Explanations

phrases related to law enforcement activities

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nat

-0.75

 prest

-0.69

 Paste

-0.61

Perfect

-0.60

Basic

-0.60

Pure

-0.58

 triv

-0.58

lua

-0.57

ocl

-0.57

beh

-0.57

POSITIVE LOGITS

 gunman

0.79

 arrests

0.79

 alleges

0.75

 arrest

0.74

 Copyright

0.73

 arrested

0.72

 inquest

0.71

 jailed

0.71

 arson

0.70

arnaev

0.69

Activations Density 0.536%

phrases related to law enforcement activities

No Comments

No Known Activations