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

Jen

-0.65

 defenses

-0.65

 Tyrann

-0.64

 Hearth

-0.64

amn

-0.63

ascript

-0.63

unia

-0.62

ordan

-0.62

Pak

-0.62

unn

-0.61

POSITIVE LOGITS

strip

0.72

 Circus

0.69

romy

0.68

mys

0.67

ened

0.65

pless

0.65

ipl

0.64

enstein

0.64

ICH

0.64

vich

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.