INDEX

Explanations

function definitions and related symbols in programming code

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

Code snippets with "new" keyword or related terms

np_acts-logits-general · gemini-2.0-flash

initializing new objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

bilisi

-0.48

ScopeManager

-0.46

akos

-0.46

AFX

-0.45

#![

-0.45

requestId

-0.45

モト

-0.42

vi

-0.42

ICS

-0.42

ัฐ

-0.42

POSITIVE LOGITS

new

1.48

new

1.45

New

1.34

New

1.33

新

1.19

NEW

1.14

NEW

1.05

 nouvelles

1.01

 nuevas

1.01

 neue

1.01

Activations Density 0.022%

function definitions and related symbols in programming code

Code snippets with "new" keyword or related terms

initializing new objects

No Comments

No Known Activations