INDEX

Explanations

code structure elements, specifically class and function definitions

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

"def" keyword in Python or other languages

np_acts-logits-general · gemini-2.0-flash

python function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

IonicModule

-0.92

 estekak

-0.81

Externé

-0.72

documentclass

-0.70

 ArrayAdapter

-0.69

DebuggerNonUser

-0.69

 matrices

-0.68

 nahilalakip

-0.67

 ligiloj

-0.66

 MessageBoxIcon

-0.66

POSITIVE LOGITS

Def

1.11

def

1.07

def

1.06

Def

0.99

DEF

0.96

DEF

0.81

 ModelExpression

0.78

 deflation

0.73

ndef

0.71

defs

0.70

Activations Density 0.051%

code structure elements, specifically class and function definitions

"def" keyword in Python or other languages

python function definitions

No Comments

No Known Activations