INDEX

Explanations

elements related to error codes or messages in programming contexts

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

Hexadecimal IDs

np_acts-logits-general · gemini-2.0-flash

numbers and indices

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

IUrlHelper

-0.88

 <>",

-0.87

ISupport

-0.82

ArrowToggle

-0.78

parsedMessage

-0.77

دانشنامهٔ

-0.76

الإنجليزية

-0.75

клопе

-0.75

WithMany

-0.75

awtextra

-0.75

POSITIVE LOGITS

Usual

0.47

出版年

0.46

homonymie

0.45

 ganchillo

0.45

 része

0.43

0.42

ēju

0.42

Activations Density 0.389%

elements related to error codes or messages in programming contexts

Hexadecimal IDs

numbers and indices

No Comments

No Known Activations