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

eric

-0.66

bows

-0.66

 Covenant

-0.62

ledged

-0.62

ersen

-0.61

nel

-0.61

ahime

-0.59

kson

-0.59

edd

-0.58

Ack

-0.58

POSITIVE LOGITS

osis

0.75

VIDIA

0.75

bol

0.72

xp

0.69

=\"

0.68

\)

0.67

":"/

0.66

 deval

0.65

ptin

0.63

VT

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.