INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

dri

-0.72

notations

-0.71

 Coil

-0.69

 coils

-0.66

DIV

-0.66

efficients

-0.65

²¾

-0.63

 coil

-0.63

 analys

-0.63

ogeneity

-0.62

POSITIVE LOGITS

BuyableInstoreAndOnline

0.78

 Booker

0.76

$.

0.70

https

0.66

JPM

0.62

 Powell

0.61

 Trayvon

0.61

 foreclosure

0.61

Das

0.60

 Chevron

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.