INDEX

Explanations

expressions of searching for information or assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 autorytatywna

-0.68

assertAll

-0.67

Lähteet

-0.64

Хьажоргаш

-0.64

IContainer

-0.63

kuuta

-0.62

Спасылкі

-0.61

'],

-0.61

 TestBed

-0.60

anmar

-0.59

POSITIVE LOGITS

 hittar

0.63

 trova

0.60

 encontraban

0.54

 trouvez

0.54

find

0.53

ussch

0.53

رشف

0.52

 paik

0.51

 насељу

0.51

 asti

0.51

Activations Density 0.256%

expressions of searching for information or assistance

No Comments

No Known Activations