INDEX

Explanations

functions and methods related to configuring or manipulating settings

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

code and markup starters

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

rungsseite

-0.71

Personensuche

-0.65

 AssemblyCulture

-0.62

QMetaType

-0.57

IntoConstraints

-0.55

 ſind

-0.52

Välislingid

-0.49

 linkovi

-0.49

clerView

-0.48

windowFixed

-0.48

POSITIVE LOGITS

setopt

0.82

RVA

0.81

 explode

0.71

implode

0.69

 implode

0.68

Cryptography

0.62

 endwhile

0.57

maxcdn

0.57

NewGuid

0.56

hibli

0.52

Activations Density 0.001%

functions and methods related to configuring or manipulating settings

code and markup starters

No Comments

No Known Activations