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

 Engineers

-0.70

 convol

-0.68

urt

-0.66

 toile

-0.65

>]

-0.63

azz

-0.63

 Torres

-0.63

ners

-0.62

 Glac

-0.61

 secondly

-0.60

POSITIVE LOGITS

raq

0.75

emonium

0.75

 piety

0.69

Reloaded

0.69

Gameplay

0.68

anos

0.68

inav

0.65

Ku

0.65

avez

0.65

 haircut

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.