INDEX

Explanations

technical terms related to image processing and health-related phrases

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

oa̍t

-0.61

 Chwiliwch

-0.56

localctx

-0.54

RTSC

-0.53

requireNonNull

-0.53

 Paglinawan

-0.52

 समीक्षाओं

-0.50

TagMode

-0.48

 saites

-0.47

fillType

-0.47

POSITIVE LOGITS

InSection

0.55

bouncycastle

0.42

 endIndex

0.39

 électroniques

0.38

 Opiniones

0.37

/**

0.36

struzione

0.36

 CORPORATION

0.35

ientras

0.35

 Infór

0.35

Activations Density 1.156%

technical terms related to image processing and health-related phrases

No Comments

No Known Activations