INDEX

Explanations

numerical values related to settings or configurations

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

Code snippets or programming-related text

np_acts-logits-general · gemini-2.0-flash

list items or measurements followed by punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ɚ

-0.53

 ویکی‌پدیا

-0.50

 ProtoMessage

-0.49

KommentareTeilen

-0.48

romic

-0.48

 Juno

-0.47

はじめに

-0.47

SOUNDBITE

-0.47

aarrggbb

-0.46

utal

-0.46

POSITIVE LOGITS

AndEndTag

0.69

 <>",

0.69

 nakalista

0.65

MigrationBuilder

0.60

awaiter

0.58

tagHelperRunner

0.54

TintMode

0.54

Française

0.53

 /\.(

0.52

oredCriteria

0.51

Activations Density 0.116%

numerical values related to settings or configurations

Code snippets or programming-related text

list items or measurements followed by punctuation

No Comments

No Known Activations