INDEX

Explanations

references to roles and performances in film and television

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

actor or character roles

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 bisog

-0.41

 farlo

-0.39

 Daarna

-0.38

UrlResolution

-0.36

 يتيمه

-0.36

uled

-0.36

asantry

-0.36

 Smithfield

-0.36

 bestaande

-0.36

 alone

-0.36

POSITIVE LOGITS

Personendaten

0.55

 EconPapers

0.53

AccessorTable

0.53

WithMany

0.49

setCharacter

0.48

Jeografia

0.47

 AssemblyVersion

0.47

 personaje

0.46

 joaat

0.44

OGND

0.44

Activations Density 0.020%

references to roles and performances in film and television

actor or character roles

No Comments

No Known Activations