INDEX

Explanations

references to performances and their critiques in films or plays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

awtextra

-0.44

 reconnu

-0.43

udara

-0.41

 dzied

-0.41

 Daarna

-0.40

 besk

-0.40

 vanske

-0.40

 mußten

-0.40

 Thrones

-0.39

 régal

-0.39

POSITIVE LOGITS

 fictional

0.70

played

0.52

 wealthy

0.51

 intptr

0.51

 titular

0.51

 corrupt

0.51

 played

0.51

 subplot

0.50

 fictitious

0.50

 neurotic

0.50

Activations Density 0.484%

references to performances and their critiques in films or plays

No Comments

No Known Activations