INDEX

Explanations

structured data or formats related to JSON serialization

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

Bonferroni correction method

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

Билгалдахарш

-0.52

 själ

-0.50

Nowhere

-0.49

TargetException

-0.48

 doInBackground

-0.48

씀

-0.48

Eins

-0.47

 חיצוניים

-0.47

Abp

-0.46

Linq

-0.46

POSITIVE LOGITS

Formatter

1.41

 formatter

1.28

formatter

1.22

DateFormatter

0.84

 Format

0.66

 FORMAT

0.59

 formats

0.59

格式

0.58

toggler

0.56

 Formats

0.56

Activations Density 0.001%

structured data or formats related to JSON serialization

Bonferroni correction method

No Comments

No Known Activations