INDEX

Explanations

terms related to technical specifications and performance metrics in computing and treatment efficacy in health contexts

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

graph sparsity and quality

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

 otomatig

-0.51

EndContext

-0.50

 esternos

-0.47

EDEFAULT

-0.47

SequentialGroup

-0.47

ollectionView

-0.47

Referanser

-0.47

guien

-0.47

Архівовано

-0.46

 lenker

-0.44

POSITIVE LOGITS

ChildScrollView

0.42

 EconPapers

0.40

лтамалар

0.37

aarrggbb

0.36

ivent

0.36

ofstream

0.35

 للمعارف

0.35

OutputPath

0.35

 reaching

0.34

rc

0.34

Activations Density 0.346%

terms related to technical specifications and performance metrics in computing and treatment efficacy in health contexts

graph sparsity and quality

No Comments

No Known Activations