INDEX

Explanations

locations and names

oai_token-act-pair · gpt-3.5-turbo

references to locations and local law enforcement entities

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

Not in Any Lists

No Comments

Negative Logits

luaj

-0.72

itatively

-0.69

isSpecialOrderable

-0.68

 SHALL

-0.68

 righteous

-0.65

 conferences

-0.64

 earnest

-0.63

 comparable

-0.63

 stricken

-0.62

 pronounced

-0.61

POSITIVE LOGITS

 Photography

0.97

photos

0.94

ulton

0.94

 Shutterstock

0.88

 screenshot

0.88

querque

0.86

ickr

0.83

)/

0.82

utterstock

0.80

reenshot

0.78

Activations Density 0.218%

locations and names

references to locations and local law enforcement entities

No Comments

No Known Activations