INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Roh

-0.72

 surn

-0.63

TBA

-0.62

 Blizzard

-0.61

 steroid

-0.61

 marijuana

-0.60

tainment

-0.60

Klu

-0.59

eport

-0.59

stan

-0.59

POSITIVE LOGITS

audi

0.75

uffed

0.72

transform

0.72

agus

0.70

overed

0.68

iddler

0.68

ored

0.68

ItemTracker

0.66

attering

0.66

uffy

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.