INDEX

Explanations

proper nouns and names in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 itſelf

-0.71

 Мексичка

-0.70

AndEndTag

-0.69

Efq

-0.61

 rempliss

-0.60

NameInMap

-0.60

Easier

-0.60

 Purg

-0.59

icrous

-0.57

^(@)

-0.57

POSITIVE LOGITS

who

0.70

Bronnen

0.52

 createContext

0.51

 living

0.51

에게

0.50

 whom

0.50

 اهل

0.50

who

0.50

Lähteet

0.49

 senior

0.49

Activations Density 0.576%

proper nouns and names in various contexts

No Comments

No Known Activations