INDEX

Explanations

comparisons in the context of improvement or deterioration

oai_token-act-pair · gpt-3.5-turbo

evaluative language related to improvement and decline

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

 entirety

-0.77

heid

-0.70

iao

-0.65

 hemisphere

-0.64

Lau

-0.63

 halves

-0.60

apple

-0.60

 holder

-0.59

ellow

-0.59

 Hong

-0.58

POSITIVE LOGITS

 sidx

0.86

 mileage

0.83

 traction

0.83

ãĤ¼

0.82

noticed

0.80

ModLoader

0.79

 veter

0.77

retty

0.74

wcs

0.72

 puberty

0.71

Activations Density 0.088%

comparisons in the context of improvement or deterioration

evaluative language related to improvement and decline

No Comments

No Known Activations