INDEX

Explanations

mathematical notation and functions related to variables and their values

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

mathematical and programming expressions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Portale

-0.65

EndGlobalSection

-0.63

 AssemblyCulture

-0.63

</thead>

-0.56

 tartalomajánló

-0.54

 Paglinawan

-0.50

 '\\;'

-0.49

لينكات

-0.48

aussian

-0.47

posedge

-0.47

POSITIVE LOGITS

 Taktlose

0.45

期刊论文

0.40

tisgarh

0.36

tangentMode

0.35

 Penge

0.34

InputBorder

0.33

httphttps

0.33

siasi

0.33

ỡng

0.33

Causes

0.32

Activations Density 0.092%

mathematical notation and functions related to variables and their values

mathematical and programming expressions

No Comments

No Known Activations