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

maps

-0.74

 neglig

-0.72

trial

-0.70

lde

-0.67

complex

-0.66

Library

-0.65

map

-0.63

library

-0.61

lat

-0.61

rences

-0.61

POSITIVE LOGITS

naire

0.84

iop

0.74

0.73

 Shanahan

0.71

arov

0.70

66666666

0.70

 guiName

0.69

 Petro

0.67

ourced

0.64

eds

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.