INDEX

Explanations

mentions of specific numbers in various formats

oai_token-act-pair · gpt-3.5-turbo

specific phrases or terms related to structures or functions in programming and technical contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Flavoring

-0.66

 fret

-0.62

 suscept

-0.56

ItemThumbnailImage

-0.56

 Vaughan

-0.56

 Spectrum

-0.55

 chirop

-0.55

 cull

-0.54

jog

-0.54

 tabl

-0.53

POSITIVE LOGITS

è¦ļéĨĴ

0.71

adobe

0.69

ãĤ¦ãĤ¹

0.67

retty

0.64

incoln

0.64

resents

0.64

ruary

0.63

argo

0.63

outhern

0.62

ogether

0.61

Activations Density 1.086%

mentions of specific numbers in various formats

specific phrases or terms related to structures or functions in programming and technical contexts

No Comments

No Known Activations