INDEX

Explanations

phrases related to rules and permissions

oai_token-act-pair · gpt-3.5-turbo

phrases regarding permission or restrictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tal

-0.71

lves

-0.68

lish

-0.66

leaf

-0.63

fish

-0.63

blow

-0.62

 Generation

-0.61

xon

-0.61

bush

-0.61

bane

-0.61

POSITIVE LOGITS

Reviewer

1.05

 exemptions

0.78

ptin

0.73

 crawl

0.69

pedia

0.69

uthor

0.68

usa

0.66

 exceptions

0.65

 plur

0.64

@@@@

0.64

Activations Density 0.049%

phrases related to rules and permissions

phrases regarding permission or restrictions

No Comments

No Known Activations