INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 mined

-0.73

rolled

-0.70

icipated

-0.69

ombs

-0.69

ained

-0.68

ubis

-0.68

reports

-0.67

ubby

-0.65

 matured

-0.65

 bowed

-0.64

POSITIVE LOGITS

pton

0.81

bucks

0.70

 Union

0.69

 Therapy

0.68

Huh

0.68

 Seah

0.67

Fed

0.67

 Card

0.66

Card

0.66

Bank

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.