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

tarians

-0.77

idable

-0.71

behind

-0.70

abwe

-0.68

eki

-0.68

 dilig

-0.67

iour

-0.66

ĪĴ

-0.65

fal

-0.65

force

-0.65

POSITIVE LOGITS

ebook

0.61

Wall

0.59

YA

0.58

sum

0.58

 glance

0.57

 denial

0.57

($

0.57

ignore

0.57

Finding

0.56

UPDATE

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.