INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

metry

-0.77

etheless

-0.74

elta

-0.66

avour

-0.64

 Divinity

-0.63

Hud

-0.62

aters

-0.61

itsch

-0.61

uddy

-0.60

opa

-0.59

POSITIVE LOGITS

ulent

0.72

ilia

0.71

spring

0.68

æ³

0.66

voice

0.65

ä¹ĭ

0.62

uated

0.59

Freedom

0.59

 circumvent

0.58

 flexible

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.