INDEX

Explanations

references to images or photographs

oai_token-act-pair · gpt-3.5-turbo

references to photos and videos

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

stood

-0.90

vernment

-0.69

phi

-0.66

pperc

-0.65

rule

-0.65

nder

-0.64

 assurance

-0.62

 denomin

-0.62

 speech

-0.61

period

-0.61

POSITIVE LOGITS

PHOTOS

1.22

 IMAGES

1.11

 PHOTO

1.09

Photos

1.06

 Images

1.03

 VIDEOS

1.02

Images

0.98

 Photograph

0.94

photos

0.93

MORE

0.89

Activations Density 0.017%

references to images or photographs

references to photos and videos

No Comments

No Known Activations