INDEX

Explanations

references to programming libraries and modules in code

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

<start_of_turn>user

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

mybatisplus

-0.59

tagext

-0.53

awtextra

-0.50

 GenerationType

-0.47

MLLoader

-0.45

webdriver

-0.42

 InputDecoration

-0.42

 womb

-0.41

Bef

-0.40

sstream

-0.40

POSITIVE LOGITS

VYMaps

0.55

TagMode

0.54

/**

0.50

ISupport

0.50

Xna

0.50

principalTable

0.50

Pranala

0.46

shortcuts

0.45

Initialize

0.45

antaine

0.44

Activations Density 0.001%

references to programming libraries and modules in code

<start_of_turn>user

No Comments

No Known Activations