INDEX

Explanations

information related to actors and their careers

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

actor performances credits

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.56

Brainz

-0.48

 >=",

-0.37

 ausser

-0.36

dataclass

-0.35

utnik

-0.35

 Hilfs

-0.35

요

-0.35

терак

-0.35

 resourceCulture

-0.34

POSITIVE LOGITS

imdb

0.54

 myſelf

0.52

 castings

0.49

HasAnnotation

0.46

 Actors

0.46

Actor

0.46

 actor

0.45

 casting

0.45

ſelf

0.45

 filmu

0.43

Activations Density 0.010%

information related to actors and their careers

actor performances credits

No Comments

No Known Activations