INDEX

Explanations

logging-related terms and actions

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

Logarithms and log-related terms

np_acts-logits-general · gemini-2.0-flash

log operations

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

 CreateTagHelper

-0.97

帖最后由

-0.89

 صوتيه

-0.78

Obrázky

-0.77

tagHelperRunner

-0.76

FunctionFlags

-0.76

ValueStyle

-0.75

HasAnnotation

-0.75

SharedDtor

-0.74

 بيها

-0.73

POSITIVE LOGITS

Slf

1.69

 logs

1.43

 Logs

1.41

log

1.40

LOG

1.36

Log

1.26

log

1.25

Logs

1.15

getLog

1.15

Log

1.11

Activations Density 0.071%

logging-related terms and actions

Logarithms and log-related terms

log operations

No Comments

No Known Activations