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

ENE

-0.83

antom

-0.74

ENCY

-0.74

ä¸Ģ

-0.72

ulas

-0.69

ILLE

-0.69

rency

-0.66

advertising

-0.66

orsche

-0.66

íķ

-0.66

POSITIVE LOGITS

 Danger

0.76

ept

0.66

 ranked

0.65

catch

0.62

 compens

0.60

 forecasts

0.60

 detects

0.58

 overest

0.57

ceans

0.57

 pessim

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.