INDEX

Explanations

references to numerical values and quantities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 <<<<<<<<<<<<<<

-0.80

 ModelExpression

-0.65

wahlen

-0.59

Castro

-0.58

 doInBackground

-0.55

 Compagn

-0.54

 eigenvectors

-0.53

 signatures

-0.53

__))

-0.53

POSITIVE LOGITS

parsedMessage

0.78

 téléphonique

0.74

 للمعارف

0.73

typeorm

0.72

 JpaRepository

0.70

TextWatcher

0.69

ApiOperation

0.67

 aDecoder

0.67

tôi

0.67

örté

0.65

Activations Density 0.129%

references to numerical values and quantities

No Comments

No Known Activations