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´ãĥ³

-0.79

 mathemat

-0.78

omore

-0.76

 obser

-0.70

agg

-0.69

lique

-0.67

 sshd

-0.67

lav

-0.66

edin

-0.65

ibl

-0.65

POSITIVE LOGITS

rest

0.75

hesis

0.71

ionage

0.68

chery

0.66

lier

0.65

trap

0.65

clus

0.64

 Slaughter

0.63

stones

0.63

 Towers

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.