INDEX

Explanations

structured data and references to tables or data outputs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

tvguidetime

-0.68

 snippetHide

-0.67



-0.66

homonymie

-0.58

épendance

-0.57

jfree

-0.54

請繼續往下閱讀

-0.53

 समीक्षाओं

-0.53

 forKey

-0.51

加坡

-0.50

POSITIVE LOGITS

 obrigado

0.57

 Lastly

0.57

 {}));

0.56

 réussite

0.56

 Please

0.55

FailureListener

0.55

 orientale

0.55

 veuillez

0.55

 Thank

0.54

 Anyways

0.54

Activations Density 0.507%

structured data and references to tables or data outputs

No Comments

No Known Activations