INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

etheless

-0.99

EStream

-0.85

cffff

-0.79

senal

-0.79

ologne

-0.78

 hemor

-0.77

idays

-0.75

packages

-0.74

userc

-0.74

 lawy

-0.73

POSITIVE LOGITS

 avoidance

0.72

 Krishna

0.68

itarian

0.65

STON

0.65

wer

0.63

digy

0.63

 Poverty

0.63

INGTON

0.62

LESS

0.61

 Hera

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.