INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

adobe

-0.73

igers

-0.72

ãĤª

-0.70

enhagen

-0.69

interstitial

-0.69

escription

-0.68

sers

-0.68

UGC

-0.67

Keefe

-0.65

isoft

-0.65

POSITIVE LOGITS

 Revis

0.64

 Reson

0.62

 Monk

0.60

})

0.60

nce

0.59

INO

0.59

 Powell

0.59

Posts

0.59

iator

0.58

'[

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.