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

reditary

-0.75

perty

-0.75

noticed

-0.74

enhagen

-0.73

lar

-0.68

ebus

-0.65

tested

-0.65

itars

-0.64

 thous

-0.63

arya

-0.63

POSITIVE LOGITS

 Chic

0.71

iop

0.64

 trad

0.63

 Contemporary

0.62

soever

0.61

board

0.61

gif

0.61

BU

0.60

 Giul

0.60

 convertible

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.