INDEX

Explanations

programming-related terms and structures related to dimensions and base units

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

audio streams or memory buffers

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

ISupport

-0.52

makeText

-0.52

 CURIAM

-0.46

PYX

-0.46

 Chwiliwch

-0.45

めでとう

-0.43

AndroidJUnit

-0.43

expandindo

-0.40

errHandler

-0.40



-0.40

POSITIVE LOGITS

 typelib

0.69

 autorytatywna

0.58

 otomatig

0.56

ьаж

0.52

Personensuche

0.49

цездатний

0.46

GEBURTSDATUM

0.45

TemporalType

0.45

 wikipagina

0.44

notifyListeners

0.44

Activations Density 0.015%

programming-related terms and structures related to dimensions and base units

audio streams or memory buffers

No Comments

No Known Activations