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

ãĤ¨

-0.71

ãĥĨãĤ£

-0.66

pload

-0.66

bound

-0.65

Wak

-0.64

iHUD

-0.64

Fed

-0.64

kick

-0.64

ãĥ£

-0.64

ika

-0.64

POSITIVE LOGITS

 Iter

0.75

arry

0.72

 Computing

0.70

 Alto

0.69

eday

0.63

EQ

0.63

dB

0.62

KT

0.61

GC

0.60

LR

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.