INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

apore

-0.79

azi

-0.74

ergy

-0.71

elist

-0.69

law

-0.63

sow

-0.63

 WARRANT

-0.61

 anecd

-0.61

azy

-0.60

 anat

-0.59

POSITIVE LOGITS

externalActionCode

0.74

 Vlad

0.71

 Cogn

0.67

Gol

0.66

 Orchestra

0.66

 Alive

0.65

 Tunisia

0.65

ĺħ

0.64

itone

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.