INDEX

Explanations

specific numerical values and associated indicators in data

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

Code snippets with hexadecimal values

np_acts-logits-general · gemini-2.0-flash

code structure delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

bootstrapcdn

-0.69

 AssemblyVersion

-0.59

DebuggerStep

-0.51

parsedMessage

-0.50

 DialogResult

-0.49

 >=",

-0.48

addPreferredGap

-0.47

 pulumi

-0.47

 GenerationType

-0.47

 LoggerFactory

-0.46

POSITIVE LOGITS

0.68

【

0.57

【

0.45

 ägg

0.45

}{

0.44

Personensuche

0.44

0.43

 CreateTagHelper

0.43

\{

0.42

){

0.41

Activations Density 0.501%

specific numerical values and associated indicators in data

Code snippets with hexadecimal values

code structure delimiters

No Comments

No Known Activations