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

minus

-0.71

naissance

-0.71

zman

-0.69

term

-0.69

zai

-0.69

 Norris

-0.68

bern

-0.68

Wars

-0.68

 cinema

-0.65

rence

-0.64

POSITIVE LOGITS

 Nanto

0.84

ngth

0.80

Ü

0.78

ignt

0.75

ĸļ

0.71

è¦ļéĨĴ

0.71

ãĤ´ãĥ³

0.68

imei

0.67

ynt

0.67

WF

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.