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

opath

-0.73

DAY

-0.71

KER

-0.66

rawdownloadcloneembedreportprint

-0.65

 Spiel

-0.65

ilk

-0.65

ak

-0.61

dar

-0.60

sul

-0.60

ascus

-0.60

POSITIVE LOGITS

¥ŀ

0.91

»

0.69

usions

0.68

abled

0.66

oslav

0.65

ONSORED

0.65

ĳ

0.62

 Laws

0.62

OSED

0.61

ceptions

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.