INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

handle

-0.81

ieth

-0.80

thy

-0.80

sts

-0.79

ls

-0.78

othe

-0.76

ropolis

-0.75

tes

-0.74

iful

-0.73

ths

-0.72

POSITIVE LOGITS

":"/

0.79

ARA

0.70

 FANTASY

0.70

 Mineral

0.68

 Bomber

0.66

 VIDEOS

0.64

 Bullets

0.64

 LINE

0.64

LINE

0.63

 FANT

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.