INDEX

Explanations

words related to art exhibitions

oai_token-act-pair · gpt-3.5-turbo

references to exhibitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ths

-0.64

 slain

-0.59

nir

-0.59

lean

-0.59

beard

-0.59

 Mole

-0.59

tera

-0.58

ntax

-0.58

oil

-0.57

 Nation

-0.57

POSITIVE LOGITS

 exhibition

1.22

 exhibitions

1.09

 Exhibition

0.94

 Thumbnails

0.93

alist

0.93

ists

0.90

ism

0.87

 catalogue

0.87

 curator

0.81

ist

0.81

Activations Density 0.016%

words related to art exhibitions

references to exhibitions

No Comments

No Known Activations