INDEX

Explanations

specific characters and symbols used in programming or scripting languages

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

Quoted strings within code or configuration files

np_acts-logits-general · gemini-2.0-flash

quoted strings and code delimiters

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 chance

-0.48

 approach

-0.48

pod

-0.45

 pole

-0.45

XmlType

-0.44

 pena

-0.44

 Observatory

-0.44

 interplay

-0.44

 observatory

-0.44

 indication

-0.43

POSITIVE LOGITS

'{@

0.65

 intStringLen

0.60

 myſelf

0.57

'"

0.56

 autorytatywna

0.56

 <>",

0.53

Efq

0.53

 Савезне

0.53

('"

0.51

\""

0.50

Activations Density 0.348%

specific characters and symbols used in programming or scripting languages

Quoted strings within code or configuration files

quoted strings and code delimiters

No Comments

No Known Activations