INDEX

Explanations

programming language keywords and function definitions

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

static func ==

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

ChildScrollView

-0.50

delwed

-0.35

>{@

-0.34

InjectAttribute

-0.34

 surla

-0.33

-0.32

esercito

-0.32

 fiume

-0.31

 그는

-0.31

peted

-0.30

POSITIVE LOGITS

staticmethod

0.55

ſelves

0.52

 censiti

0.51

umbia

0.51

JvmStatic

0.50

 PyLong

0.50

 själva

0.48

NameInMap

0.47

uey

0.47

 ourselves

0.47

Activations Density 0.005%

programming language keywords and function definitions

static func ==

No Comments

No Known Activations