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

Trend

-0.74

Rated

-0.68

)</

-0.68

Ing

-0.67

 Letter

-0.64

Hug

-0.62

WW

-0.62

Interest

-0.60

TO

-0.60

LET

-0.60

POSITIVE LOGITS

bris

0.81

arre

0.79

acca

0.75

ety

0.71

ija

0.65

usra

0.65

eers

0.64

ulia

0.64

iba

0.64

amura

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.