INDEX

Explanations

positive descriptions of acting performances

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ilaire

-0.46

Ptr

-0.44

ην

-0.44

 simplifié

-0.42

setBorder

-0.42

ieteur

-0.41

clearInterval

-0.41

歌词

-0.41

節目

-0.41

 Sécurité

-0.41

POSITIVE LOGITS

 actors

1.08

 actor

0.99

 actress

0.97

 Actor

0.92

 Actors

0.92

 actresses

0.92

Actors

0.89

actors

0.86

 acting

0.83

Actor

0.82

Activations Density 0.198%

positive descriptions of acting performances

No Comments

No Known Activations