INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 partName

-0.72

arist

-0.65

ãĥ¼ãĥ³

-0.63

 Indies

-0.63

 Colon

-0.62

Topics

-0.62

WTC

-0.61

 Hudson

-0.59

console

-0.59

iliation

-0.58

POSITIVE LOGITS

 undert

0.70

luster

0.70

earch

0.69

soDeliveryDate

0.68

htaking

0.66

cius

0.64

urg

0.64

eton

0.63

afety

0.62

plain

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.