INDEX

Explanations

references to paintings or artworks

oai_token-act-pair · gpt-3.5-turbo

references to paintings

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

nir

-0.79

reme

-0.77

reek

-0.76

ornia

-0.74

aucus

-0.72

cgi

-0.72

aspx

-0.71

abad

-0.71

UU

-0.70

DN

-0.70

POSITIVE LOGITS

 painter

1.14

 paintings

1.12

 depicting

1.06

 painting

1.03

 artwork

0.91

wright

0.91

 Painting

0.88

 portraits

0.87

 portraying

0.85

isans

0.85

Activations Density 0.021%

references to paintings or artworks

references to paintings

No Comments

No Known Activations