INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

NetMessage

-0.88

ague

-0.75

 Aval

-0.70

teenth

-0.63

 airspace

-0.61

onomous

-0.61

 Arist

-0.59

 faire

-0.58

 Wild

-0.57

 Commun

-0.57

POSITIVE LOGITS

ittens

0.80

wagon

0.76

 spons

0.73

omination

0.69

kefeller

0.69

aminer

0.68

visor

0.68

itus

0.65

ogle

0.64

hovah

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.