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

©¶æ¥µ

-0.74

²¾

-0.69

 Cree

-0.68

 booster

-0.68

 Booster

-0.66

ĳå£«

-0.65

 Colts

-0.65

GHC

-0.62

 Texans

-0.62

 contractors

-0.61

POSITIVE LOGITS

ancial

0.77

":["

0.73

mary

0.73

capital

0.71

tsky

0.70

Jesus

0.69

 Bark

0.69

igion

0.67

ivist

0.64

Miami

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.