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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eus

-0.74

walk

-0.73

sett

-0.73

fill

-0.72

christ

-0.70

-0.69

issors

-0.66

found

-0.65

essor

-0.65

ipop

-0.64

POSITIVE LOGITS

ynchronous

0.73

²¾

0.72

pire

0.72

ynchron

0.71

 Brill

0.69

eting

0.68

 exha

0.68

ets

0.67

©¶æ

0.66

ETS

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.