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

Prince

-0.83

SEE

-0.77

SPA

-0.77

SE

-0.75

Planet

-0.75

BUS

-0.73

TEXTURE

-0.72

CONT

-0.72

POSE

-0.72

FF

-0.71

POSITIVE LOGITS

 pesky

0.78

rical

0.74

ional

0.72

uning

0.70

mental

0.70

tons

0.69

akedown

0.68

hed

0.68

 slightest

0.66

 aggregate

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.