INDEX

Explanations

references to photos or photography

oai_token-act-pair · gpt-3.5-turbo

instances of the word "photo."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

orse

-0.79

cair

-0.78

ulhu

-0.74

ciating

-0.74

steen

-0.71

ricular

-0.69

urous

-0.66

rencies

-0.66

Poe

-0.64

lear

-0.63

POSITIVE LOGITS

journal

1.46

 gallery

1.15

ynthesis

1.08

 album

1.04

ynt

1.01

 galleries

1.01

ops

1.01

 booth

0.99

album

0.97

electric

0.96

Activations Density 0.045%

references to photos or photography

instances of the word "photo."

No Comments

No Known Activations