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

CTV

-0.73

itta

-0.70

ieu

-0.69

CCC

-0.67

beit

-0.66

isma

-0.66

bal

-0.66

minus

-0.65

Bok

-0.65

endi

-0.65

POSITIVE LOGITS

MpServer

0.98

hol

0.73

 unfocusedRange

0.70

 Rept

0.67

 Gest

0.66

 Heller

0.65

EStream

0.64

 Weapons

0.63

aneously

0.62

awaru

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.