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

outs

-0.62

hen

-0.62

Otherwise

-0.61

 surrounds

-0.61

 immersion

-0.61

 appropriated

-0.60

 reefs

-0.60

earable

-0.60

pocket

-0.59

-0.58

POSITIVE LOGITS

arest

0.89

interstitial

0.82

ntil

0.78

hess

0.76

Son

0.76

»Ĵ

0.72

 tremend

0.71

cyclopedia

0.71

loo

0.70

Image

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.