INDEX

Explanations

descriptors of physical conditions and traits, particularly negative or unpleasant attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 للاسماء

-0.76

AndEndTag

-0.71

 lenker

-0.70

 ModelExpression

-0.68

LookAnd

-0.68

yntaxException

-0.61

存于互联网档案馆

-0.60

 femei

-0.57

 nahilalakip

-0.57

 AssemblyCulture

-0.56

POSITIVE LOGITS

afficheront

0.61

جغرافيا

0.57

NetworkInfo

0.55

^(@)

0.55

ENDO

0.55

Portale

0.52

ingar

0.52

ellemző

0.51

بوابة

0.50

}{*}{}

0.50

Activations Density 0.807%

descriptors of physical conditions and traits, particularly negative or unpleasant attributes

No Comments

No Known Activations