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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Thompson

-0.74

ãģ®

-0.72

âĢ¢âĢ¢

-0.71

Thom

-0.71

onto

-0.69

ãģį

-0.69

rued

-0.69

xit

-0.68

vt

-0.68

ety

-0.67

POSITIVE LOGITS

 egalitarian

0.74

 herself

0.68

abase

0.65

 unsus

0.64

 resil

0.60

 twins

0.59

 admire

0.59

 Firm

0.59

 estim

0.58

igans

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.