INDEX

Explanations

numbers in various sequences

oai_token-act-pair · gpt-3.5-turbo

numerical values or metrics related to beauty or aesthetic assessments

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

 millenn

-0.89

 nomine

-0.84

 corrid

-0.83

 withd

-0.77

 referen

-0.74

reon

-0.73

Nitrome

-0.73

ThumbnailImage

-0.72

 tremend

-0.72

ÃĥÃĤÃĥÃĤ

-0.70

POSITIVE LOGITS

 partName

1.14

ãģ®æ

0.78

çİĭ

0.77

0.76

Activations Density 0.070%

numbers in various sequences

numerical values or metrics related to beauty or aesthetic assessments

No Comments

No Known Activations