INDEX

Explanations

key programming terms related to types and parameters in a function context

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

المناصب

-0.65

saraba

-0.62

AnchorStyles

-0.61

 transférez

-0.59

 informée

-0.58

 intptr

-0.57

nloa

-0.56

parsedMessage

-0.52

 '\\;'

-0.51

 CURLOPT

-0.50

POSITIVE LOGITS

 enoj

0.42

TypedValue

0.39

AttributeSet

0.35

definecolor

0.35

 TECHNICAL

0.34

HasIndex

0.34

 prisa

0.33

 Innen

0.33

 Landwir

0.33

 Einzel

0.32

Activations Density 0.283%

key programming terms related to types and parameters in a function context

No Comments

No Known Activations