INDEX

Explanations

references to README files and non-numbered sections in documents

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

LaTeX math notation

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

 betweenstory

-0.94

GEBURTSDATUM

-0.78

 queſta

-0.75

Spoljašnje

-0.63

webElementXpaths

-0.62

__":

-0.59

createCanvas

-0.58

 PeEnEo

-0.55

TypedDataSet

-0.54

Personendaten

-0.52

POSITIVE LOGITS

httphttps

0.59

ViewFeatures

0.52

ResumeLayout

0.45

 also

0.44

[]:

0.40

usercontent

0.39

 Saltar

0.39

 Also

0.38

 here

0.38

 <<<<<<<<<<<<<<

0.38

Activations Density 0.000%

references to README files and non-numbered sections in documents

LaTeX math notation

No Comments

No Known Activations