INDEX

Explanations

terms related to specific methodologies and classifications in scientific or technical contexts

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

technical and scientific terms

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

出版年

-0.40

 NSCoder

-0.40

AutoScaleMode

-0.38

 flotante

-0.36

SharedDtor

-0.35

__*/

-0.34

InjectMocks

-0.34

éroport

-0.34

دانشنامهٔ

-0.34

脚注の使い方

-0.33

POSITIVE LOGITS

 propOrder

0.47

Extended

0.46

 EClass

0.41

addPreferredGap

0.40

 ConstraintSet

0.40

ありますが

0.40

 Extended

0.39

 Glou

0.39

 supplementary

0.39

DllImport

0.38

Activations Density 0.105%

terms related to specific methodologies and classifications in scientific or technical contexts

technical and scientific terms

No Comments

No Known Activations