INDEX

Explanations

references to specific names or entities, particularly in scientific and legal contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Capitalized word fragments

np_acts-logits-general · gemini-2.0-flash

proper names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

Negative Logits

MigrationBuilder

-1.15

 disambiguazione

-1.06

 Paglinawan

-1.05

 '\\;'

-0.98

NameInMap

-0.97

Personendaten

-0.96

WebVitals

-0.95

webElementXpaths

-0.94

SequentialGroup

-0.94

 nahilalakip

-0.93

POSITIVE LOGITS

Fre

0.50

0.49

0.47

fre

0.45

0.44

Co

0.44

يمق

0.44

Mar

0.44

Activations Density 0.537%

references to specific names or entities, particularly in scientific and legal contexts

Capitalized word fragments

proper names

No Known Activations