INDEX

Explanations

terms and parameters related to configuration and settings in programming or technical documentation

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

disable program

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

windowFixed

-0.52

LookAnd

-0.51

ніципа

-0.36

хьтан

-0.35

multicolumn

-0.34

GenerationType

-0.32

 HttpNotFound

-0.32

 autorytatywna

-0.31

parsedMessage

-0.30

 fallu

-0.29

POSITIVE LOGITS

 насељу

0.58

 MainAxisSize

0.57

OrNil

0.57

ToBounds

0.55

 विश्वसनीयता

0.55

 препратки

0.54

Hentet

0.54

WebVitals

0.53

jspb

0.53

usercontent

0.52

Activations Density 0.082%

terms and parameters related to configuration and settings in programming or technical documentation

disable program

No Comments

No Known Activations