INDEX

Explanations

technical definitions and identifiers in programming or documentation contexts

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

C macros and bitwise operations

np_acts-logits-general · gemini-2.0-flash

commands and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

 Chwiliwch

-1.00

Diweddarwch

-0.98

 المعيارى

-0.91

 CreateTagHelper

-0.89

aarrggbb

-0.89

abestanden

-0.88

########.

-0.87

DockStyle

-0.85

WithIOException

-0.85

 Administrativna

-0.84

POSITIVE LOGITS

</strong>

0.28

 combined

0.28

мум

0.27

ise

0.26

 mesmo

0.25

 needs

0.25

েই

0.25

 without

0.25

Và

0.24

 viens

0.23

Activations Density 2.386%

technical definitions and identifiers in programming or documentation contexts

C macros and bitwise operations

commands and identifiers

No Comments

No Known Activations