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

aminer

-0.85

yip

-0.81

foreseen

-0.79

ournal

-0.76

omething

-0.75

ictionary

-0.73

oaded

-0.72

 Trader

-0.70

itialized

-0.69

ymm

-0.68

POSITIVE LOGITS

ATH

0.78

 Bald

0.68

athi

0.68

Wat

0.67

sted

0.67

zar

0.65

 Bolton

0.62

 Rossi

0.61

Ä

0.61

AKING

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.