INDEX

Explanations

references to various libraries or collections of resources

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

"library" and related terms

np_acts-logits-general · gemini-2.0-flash

library / libraries

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IndentedString

-0.86

 disponibilités

-0.83

parseFrom

-0.81

makeConstraints

-0.81

MigrationBuilder

-0.75

 Lesnar

-0.75

Vidite

-0.74

omitempty

-0.73

 Crot

-0.73

CTS

-0.72

POSITIVE LOGITS

 libraries

1.32

 Libraries

1.26

 library

1.22

 Library

1.05

libraries

1.04

Libraries

1.03

ibrary

0.95

Library

0.94

 LIBRARY

0.94

 bibliothèque

0.93

Activations Density 0.090%

references to various libraries or collections of resources

"library" and related terms

library / libraries

No Comments

No Known Activations