INDEX

Explanations

references to data structures, attributes, and commands related to programming or computational tasks

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

Code snippets with colons, commas, and symbols

np_acts-logits-general · gemini-2.0-flash

technical symbols and abbreviations

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

msgTypes

-0.56

-------

-0.54

 AssemblyTitle

-0.48

 isActive

-0.44

ViewFeatures

-0.44

Chham

-0.44

 AspNetCore

-0.44

WriteBarrier

-0.44

rungsseite

-0.44

urlopen

-0.43

POSITIVE LOGITS

 resourceCulture

0.42

igkeit

0.38

WEBPACK

0.37

eltzer

0.37

ATURE

0.35

dq

0.35

 ब्रेकडाउन

0.34

 desglose

0.34

LEGGI

0.34

 Schal

0.32

Activations Density 1.023%

references to data structures, attributes, and commands related to programming or computational tasks

Code snippets with colons, commas, and symbols

technical symbols and abbreviations

No Comments

No Known Activations