INDEX

Explanations

references to notable actors and their roles or performances in film

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

ViewImports

-0.44

']>;

-0.44

pexpr

-0.44

:+:

-0.42

utnik

-0.41

awtextra

-0.41

RefNanny

-0.40

tagHelperRunner

-0.39

 IOError

-0.39

crollView

-0.39

POSITIVE LOGITS

 portraying

1.29

 portrayal

1.11

 roles

1.11

 portray

1.08

 playing

1.08

 portrays

1.05

 portrayed

1.00

 role

1.00

 starring

0.96

 interpretar

0.94

Activations Density 0.358%

references to notable actors and their roles or performances in film

No Comments

No Known Activations