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

theless

-0.81

 therap

-0.77

 acknow

-0.68

nown

-0.66

 contrace

-0.65

 proble

-0.65

utherford

-0.63

odder

-0.62

ancial

-0.62

iae

-0.62

POSITIVE LOGITS

uga

0.74

################

0.73

enario

0.72

ADA

0.68

senal

0.66

SD

0.65

ĻĤ

0.65

grad

0.62

 ambul

0.62

ħĭ

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.