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

poons

-0.85

anship

-0.79

è¦ļéĨĴ

-0.78

arsh

-0.71

aja

-0.68

chnology

-0.66

nown

-0.66

 mentors

-0.64

 Goddard

-0.64

olt

-0.64

POSITIVE LOGITS

Liberal

0.71

Sing

0.68

isy

0.68

Republicans

0.67

Hong

0.66

âĸ

0.66

VID

0.63

Pie

0.63

Tai

0.62

Û

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.