INDEX

Explanations

references or mentions of image galleries in a text

oai_token-act-pair · gpt-3.5-turbo

mention of galleries and exhibitions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aneously

-0.72

ties

-0.71

aneous

-0.67

etheless

-0.65

jab

-0.65

mental

-0.65

 Contra

-0.64

ono

-0.63

ality

-0.63

ially

-0.63

POSITIVE LOGITS

 Thumbnails

1.23

 galleries

1.15

 gallery

1.13

 exhibitions

1.00

Gallery

0.97

 exhibition

0.93

 Gallery

0.92

gallery

0.90

opus

0.81

 showcasing

0.78

Activations Density 0.030%

references or mentions of image galleries in a text

mention of galleries and exhibitions

No Comments

No Known Activations