INDEX

Explanations

references to actors and their performances in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Glaser

-0.50

 newsletter

-0.44

izze

-0.43

 sola

-0.42

mä

-0.41

peti

-0.41

 Bree

-0.40

Phaser

-0.40

awar

-0.40

adalupe

-0.39

POSITIVE LOGITS

 actor

1.20

 actors

1.18

 Actor

1.10

 Actors

1.08

Actor

1.02

 actress

1.01

 actores

0.99

 skues

0.98

 actresses

0.97

Actors

0.95

Activations Density 0.186%

references to actors and their performances in various contexts

No Comments

No Known Activations