INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

abal

-0.75

dylib

-0.70

idon

-0.67

 Eternity

-0.66

 Amend

-0.65

aukee

-0.64

 Dele

-0.64

apeshifter

-0.63

 Bombs

-0.59

BALL

-0.59

POSITIVE LOGITS

rice

0.74

wagen

0.74

ropolitan

0.69

å·

0.65

catentry

0.65

ãĥĦ

0.65

chairs

0.64

assetsadobe

0.63

adden

0.63

 deprecated

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.