INDEX

Explanations

descriptions of images

oai_token-act-pair · gpt-3.5-turbo

references to images or visual depictions 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 @ 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

ance

-0.92

angan

-0.85

mental

-0.82

vernment

-0.78

cession

-0.77

cknow

-0.76

alities

-0.76

forestation

-0.75

ament

-0.75

acies

-0.74

POSITIVE LOGITS

 Thumbnails

1.03

 IMAGES

0.91

 pictured

0.86

 gallery

0.82

 Photographer

0.80

 Gallery

0.79

 Buckingham

0.79

 Scenes

0.76

 HuffPost

0.75

 Pict

0.75

Activations Density 0.024%

descriptions of images

references to images or visual depictions in the text

No Comments

No Known Activations