INDEX

Explanations

mentions of actors and their film credits

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

acting roles or appearances

np_acts-logits-general · gemini-2.0-flash

actor roles and appearances

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

protoimpl

-0.48

andaş

-0.48

multer

-0.47

 térm

-0.45

 mecán

-0.44

請繼續往下閱讀

-0.43

(~(

-0.42

 ekst

-0.40

 conformidad

-0.39

 invokingState

-0.39

POSITIVE LOGITS

 starring

0.47

 appearances

0.47

 roles

0.46

 appearing

0.45

 cameo

0.44

 appeared

0.41

ďaka

0.40

 Roles

0.40

 Appearances

0.40

 filmed

0.39

Activations Density 0.085%

mentions of actors and their film credits

acting roles or appearances

actor roles and appearances

No Comments

No Known Activations