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

alg

-0.79

GET

-0.75

Issue

-0.74

£ı

-0.73

Methods

-0.68

çīĪ

-0.66

METHOD

-0.66

utterstock

-0.66

roup

-0.66

Construct

-0.65

POSITIVE LOGITS

 scient

0.66

 Lonely

0.65

ified

0.65

Sr

0.64

 Slay

0.63

 distinguished

0.61

hovah

0.60

ifies

0.59

 Sabbath

0.59

 emphasized

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.