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

 acrylic

-0.85

 WATCHED

-0.78

Pv

-0.76

 mats

-0.70

eki

-0.62

 ILCS

-0.62

 Studio

-0.62

Iw

-0.61

iger

-0.60

 Lansing

-0.60

POSITIVE LOGITS

ĪĴ

0.69

ļéĨĴ

0.68

draft

0.67

word

0.67

agg

0.67

Ĺ

0.66

checked

0.65

Psy

0.64

²

0.64

'.

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.