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

isure

-0.73

itations

-0.69

ouls

-0.68

inton

-0.65

apons

-0.65

 Batt

-0.64

vation

-0.63

itate

-0.63

å£«

-0.63

arettes

-0.62

POSITIVE LOGITS

ICAN

0.74

Reloaded

0.72

hetical

0.64

 Lancaster

0.63

aceae

0.61

raq

0.60

ãĥ¯ãĥ³

0.59

 mine

0.59

cffffcc

0.59

 truce

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.