INDEX

Explanations

patterns or structures related to programming functions and their outputs

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

code delimiters and abbreviations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

AndEndTag

-0.62

 nakalista

-0.47

 ModelExpression

-0.46

Nuorodos

-0.44

RTSN

-0.44

:+:

-0.43

 chì

-0.42

rungsseite

-0.41

devamını

-0.41

yii

-0.40

POSITIVE LOGITS

LabelTagHelper

0.60

ArgumentParser

0.47

<?

0.46

DrawerToggle

0.43

UrlResolution

0.42

LEncoder

0.40

()][

0.38

 invokingState

0.37

shadowRadius

0.36

ionista

0.35

Activations Density 0.213%

patterns or structures related to programming functions and their outputs

code delimiters and abbreviations

No Comments

No Known Activations