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

 Gibson

-0.67

chool

-0.66

entially

-0.64

ãĢį

-0.62

 fixme

-0.61

 Tone

-0.60

 Ning

-0.60

 Gohan

-0.60

 deduction

-0.59

ino

-0.59

POSITIVE LOGITS

][

0.76

veyard

0.71

letal

0.68

aptic

0.66

ombies

0.65

ethy

0.63

 thirst

0.63

utonium

0.62

ptic

0.61

ighth

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.