INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

inventoryQuantity

-0.79

paren

-0.78

lees

-0.76

lez

-0.75

isSpecialOrderable

-0.70

lication

-0.69

illard

-0.66

\\\\

-0.65

externalActionCode

-0.64

 Flavoring

-0.64

POSITIVE LOGITS

ichi

0.75

kus

0.65

 dues

0.62

 control

0.62

alties

0.60

uses

0.59

orum

0.57

 Chips

0.57

 Arabian

0.57

 feudal

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.