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

usted

-0.93

agos

-0.88

henko

-0.79

riot

-0.78

isons

-0.74

atform

-0.74

ropolitan

-0.74

rals

-0.73

wegian

-0.72

cedented

-0.72

POSITIVE LOGITS

Streamer

0.78

ãĤ¶

0.69

 Herrera

0.66

Clinton

0.65

ATE

0.65

0.64

å·

0.64

 bias

0.62

 debates

0.62

à¥

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.