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

heim

-0.78

¿½

-0.71

heid

-0.67

cair

-0.66

ĸļ

-0.66

 Shang

-0.65

hov

-0.64

Sources

-0.64

inki

-0.63

gypt

-0.61

POSITIVE LOGITS

Balt

0.68

 proclamation

0.65

jug

0.64

 Balt

0.63

rew

0.62

rants

0.62

voc

0.61

 Ampl

0.60

atform

0.59

Rak

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.