INDEX

Explanations

code-related definitions, specifically focusing on parameters and formatting elements in programming and data structures

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

BufferException

-0.50

Autoritní

-0.46

 propOrder

-0.44

GEBURTS

-0.40

исленность

-0.40

RTEE

-0.40

 <<<<<<<<<<<<<<

-0.39

BASEPATH

-0.38

<?

-0.37

 eens

-0.34

POSITIVE LOGITS

tvguidetime

0.56

ValueStyle

0.49

RenderAtEndOf

0.48

 renounce

0.47

 accès

0.46

 Pepper

0.46

 linkovi

0.45

cimiento

0.44

 moschino

0.44

 bento

0.44

Activations Density 1.269%

code-related definitions, specifically focusing on parameters and formatting elements in programming and data structures

No Comments

No Known Activations