INDEX

Explanations

references to actors or actor-related terms within a code context

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

actor or actress

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

 Lind

-0.54

 Lindberg

-0.52

 Shimizu

-0.52

 Saunders

-0.50

 Neuf

-0.49

 Guadalupe

-0.49

Zu

-0.48

 Griswold

-0.48

 Gund

-0.48

 Louise

-0.47

POSITIVE LOGITS

Actor

0.97

Actors

0.97

 Actor

0.96

 Actors

0.88

actor

0.84

 actors

0.82

 actor

0.82

actors

0.75

 acteur

0.71

 actores

0.70

Activations Density 0.005%

references to actors or actor-related terms within a code context

actor or actress

No Comments

No Known Activations