INDEX

Explanations

brands, product names, and organizational entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.50

 sarili

-0.49

💇

-0.46

telen

-0.46

 científicas

-0.45

cosity

-0.44

lapi

-0.43

 celle

-0.43

epiece

-0.43

 EnglishChoose

-0.43

POSITIVE LOGITS

Referințe

0.64

 <<<<<<<<<<<<<<

0.62

expandindo

0.59

 GENERATED

0.59

 juſt

0.57

achite

0.57

DispatchToProps

0.57

例句

0.57

िखित

0.56

 onely

0.56

Activations Density 0.414%

brands, product names, and organizational entities

No Comments

No Known Activations