INDEX

Explanations

references to images or photographs

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pictures"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

osi

-0.83

ressive

-0.71

 Revel

-0.68

merce

-0.66

Beg

-0.66

avanaugh

-0.66

endez

-0.65

 denomin

-0.64

ggles

-0.64

owder

-0.64

POSITIVE LOGITS

ynthesis

0.99

 depicting

0.96

 galleries

0.94

Pict

0.92

ynt

0.91

 pictures

0.87

 pics

0.86

 images

0.86

 Thumbnails

0.84

 IMAGES

0.82

Activations Density 0.021%

references to images or photographs

instances of the word "pictures"

No Comments

No Known Activations