INDEX

Explanations

code and programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Jîn

-0.59

addGap

-0.56

ніципалі

-0.51

OrNil

-0.50

 Citations

-0.50

 препратки

-0.49

蚪

-0.49

✭✭

-0.47

⪧

-0.47

fach

-0.46

POSITIVE LOGITS

 disambiguazione

0.50

 sauvages

0.39

saraba

0.36

ExtendWith

0.35

enderror

0.35

 suivants

0.34

 armées

0.34

 noDo

0.33

 vilja

0.32

 particuliers

0.32

Activations Density 1.288%

code and programming-related terms

No Comments

No Known Activations