INDEX

Explanations

images or visual descriptions indicated with the word "pictured"

oai_token-act-pair · gpt-3.5-turbo

references to images and their locations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 increment

-0.72

 dependency

-0.62

 Distribution

-0.62

 Â±

-0.61

 reasonable

-0.61

 appreci

-0.61

lin

-0.61

 extension

-0.59

 dependence

-0.59

 fatigue

-0.59

POSITIVE LOGITS

pictured

3.87

above

1.66

shown

1.66

below

1.40

 pictured

1.36

left

1.24

SPONSORED

1.21

sic

1.19

seen

1.13

Scroll

1.11

Activations Density 0.021%

images or visual descriptions indicated with the word "pictured"

references to images and their locations in the text

No Comments

No Known Activations