INDEX

Explanations

locations or references to specific geographic entities or international contexts

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

with mixed-case letters

np_acts-logits-general · gemini-2.0-flash

documentation links

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

>--}}

-0.59

zian

-0.54

luß

-0.54

protoimpl

-0.51

MAS

-0.49

 Things

-0.49

rians

-0.49

Cris

-0.48

ViewImports

-0.48

ReusableCell

-0.48

POSITIVE LOGITS

DockStyle

0.74

LookAnd

0.70

 autorytatywna

0.62

Notae

0.59

WIDE

0.59

byshev

0.59

RegistryLite

0.59

wide

0.57

actéristique

0.56

saraba

0.56

Activations Density 0.140%

locations or references to specific geographic entities or international contexts

with mixed-case letters

documentation links

No Comments

No Known Activations