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

cffff

-1.04

ofi

-0.80

acca

-0.78

culus

-0.76

aspers

-0.74

agin

-0.71

uana

-0.71

ntil

-0.68

aja

-0.66

rison

-0.65

POSITIVE LOGITS

 posted

0.67

 Metal

0.66

 Cross

0.65

ãĤ¨ãĥ«

0.61

 Zeal

0.61

 cosmos

0.61

 Papers

0.59

 shade

0.59

ãĥĨ

0.58

 aired

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.