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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lazarus

-0.67

fa

-0.65

fs

-0.65

IQ

-0.62

 reperto

-0.62

ites

-0.61

ph

-0.60

pra

-0.60

Jac

-0.59

Score

-0.59

POSITIVE LOGITS

 Sabha

0.89

ursed

0.75

esson

0.72

ixels

0.71

ubes

0.69

ategory

0.68

tymology

0.68

upid

0.68

enhagen

0.68

ensibly

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.