INDEX

Explanations

descriptions related to physical characteristics and personal histories

oai_token-act-pair · gpt-3.5-turbo

aspects related to societal issues and demographics

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

nesday

-0.95

Benz

-0.83

pse

-0.73

IRC

-0.71

"]=>

-0.70

atech

-0.70

norm

-0.70

requently

-0.70

ribly

-0.70

sic

-0.69

POSITIVE LOGITS

 overlap

0.83

tow

0.78

 backgrounds

0.75

 spare

0.75

 sway

0.75

 background

0.74

 twist

0.74

 flair

0.73

 backing

0.72

 flowing

0.72

Activations Density 0.758%

descriptions related to physical characteristics and personal histories

aspects related to societal issues and demographics

No Comments

No Known Activations