INDEX

Explanations

programming terms and syntactical structures related to data management and manipulation

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

Code-related terms

np_acts-logits-general · gemini-2.0-flash

code structures and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

UnusedPrivate

-0.83

LookAnd

-0.70

 "..\..\..\

-0.62

ordinaire

-0.59

evs

-0.55

PreferredItem

-0.53

ivably

-0.53

pide

-0.53

 "..\..\

-0.52

gyz

-0.52

POSITIVE LOGITS

ंदीखरीदारी

0.75

 kasarigan

0.64

########.

0.59

AxisAlignment

0.58

 AssemblyTitle

0.50

CDCl

0.50

 snippetHide

0.49

RefNanny

0.47

 Référence

0.46

RTGC

0.43

Activations Density 0.162%

programming terms and syntactical structures related to data management and manipulation

Code-related terms

code structures and identifiers

No Comments

No Known Activations