INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ory

-0.67

orage

-0.66

otech

-0.63

obook

-0.63

auga

-0.63

ocry

-0.62

ias

-0.61

omorph

-0.61

yrus

-0.60

oring

-0.60

POSITIVE LOGITS

NPR

0.78

 Guant

0.73

illet

0.72

debian

0.67

Gru

0.65

lp

0.63

Gar

0.62

arser

0.61

Äĩ

0.61

Äį

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.