INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

iland

-0.84

pages

-0.74

 unpop

-0.72

ileaks

-0.70

TPS

-0.69

debian

-0.69

rg

-0.66

nown

-0.66

rl

-0.66

interstitial

-0.65

POSITIVE LOGITS

ãĤ¦ãĤ¹

0.96

ãĤ¹ãĥĪ

0.64

elligence

0.64

orem

0.64

 phenotype

0.62

 initials

0.62

rium

0.62

æ©Ł

0.62

arij

0.61

nance

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.