INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 projection

-0.68

ldom

-0.66

 livest

-0.65

 exha

-0.64

 appeal

-0.63

 Phant

-0.63

Ga

-0.62

 Admission

-0.62

 fullest

-0.62

coe

-0.62

POSITIVE LOGITS

omic

0.74

xon

0.73

][

0.71

bucks

0.70

Rew

0.67

Iss

0.64

reads

0.63

Published

0.63

Fix

0.62

Leaks

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.