INDEX

Explanations

patterns and structures related to data processing and management, particularly in CSV files

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

header and data manipulation

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

Personensuche

-0.53

Datuak

-0.46

 transfieras

-0.45

 ویکی‌پدیا

-0.44

 Numerade

-0.41

Tikang

-0.39

AddTagHelper

-0.39

Hentet

-0.38

Климат

-0.38

 ffilmiau

-0.36

POSITIVE LOGITS

writerow

0.54

 desmotivaciones

0.45

moveToFirst

0.43

BackStack

0.42

MessageState

0.40

 OMITBAD

0.40

GIVEREF

0.40

fetchone

0.40

NSArray

0.39

gehend

0.38

Activations Density 0.006%

patterns and structures related to data processing and management, particularly in CSV files

header and data manipulation

No Comments

No Known Activations