INDEX

Explanations

programming-related terms and structures, particularly in the context of game mechanics or AI behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

MessageTagHelper

-0.44

<?

-0.40

XtraEditors

-0.38

RegistryLite

-0.38

 ब्रेकडाउन

-0.37

Neu

-0.37



-0.37

CopyWith

-0.36

Попис

-0.36

 creativity

-0.36

POSITIVE LOGITS

posedge

0.62

 target

0.52

StoryboardSegue

0.49

Panamoan

0.48

лтамалар

0.48

target

0.47

 كومونز

0.45

 Superan

0.44

 TARGET

0.43

GEBURTSDATUM

0.43

Activations Density 0.232%

programming-related terms and structures, particularly in the context of game mechanics or AI behavior

No Comments

No Known Activations