INDEX

Explanations

references to languages, particularly those spoken in specific regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 createSprite

-0.54

JsonHelper

-0.53

 للاسماء

-0.53

AndEndTag

-0.52

contentLoaded

-0.51

clusal

-0.51

VIAF

-0.50

 disambiguazione

-0.50

енча

-0.50

 bekasi

-0.50

POSITIVE LOGITS

 مشارکت‌کنندگان

0.58

kun

0.57

euc

0.55

 Bool

0.53

География

0.53

native

0.53

ftagPool

0.52

клопе

0.52

 native

0.51

Euc

0.51

Activations Density 0.124%

references to languages, particularly those spoken in specific regions

No Comments

No Known Activations