INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

emin

-0.69

lin

-0.66

bia

-0.65

chn

-0.64

 grading

-0.64

asy

-0.63

unin

-0.63

Murray

-0.63

held

-0.62

assi

-0.62

POSITIVE LOGITS

FU

0.71

pei

0.70

 Caption

0.68

 embodiment

0.67

 Detective

0.65

 smugg

0.63

 Murd

0.60

Guy

0.60

 mang

0.60

 Constable

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.