INDEX

Explanations

references to authors and collaborators in academic or scientific contexts

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

Initials (A-Z) following a name

np_acts-logits-general · gemini-2.0-flash

names with initials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

MigrationBuilder

-1.27

Personensuche

-1.14

Geplaatst

-1.14

 ModelExpression

-1.04

EndProject

-1.01

 Anſ

-1.01

 ComVisible

-0.99

-------------</

-0.95

StructEnd

-0.95

 AspNetCore

-0.95

POSITIVE LOGITS

1.90

1.83

1.72

1.70

1.69

1.68

1.64

1.60

1.58

Activations Density 0.708%

references to authors and collaborators in academic or scientific contexts

Initials (A-Z) following a name

names with initials

No Comments

No Known Activations