INDEX

Explanations

log statements related to events and warnings in the context of application logging

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

Log messages (info, warn, debug)

np_acts-logits-general · gemini-2.0-flash

logging information debug warn

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

DockStyle

-0.64

mergeFrom

-0.61

 mouvements

-0.59

DialogContent

-0.58

 coinvol

-0.56

 volont

-0.56

parsedMessage

-0.55

 Exactos

-0.54

CardContent

-0.54

olm

-0.54

POSITIVE LOGITS

info

0.86

 info

0.75

debug

0.73

 warn

0.63

INFO

0.62

Info

0.62

 debug

0.60

 Info

0.59

warn

0.59

 INFO

0.59

Activations Density 0.136%

log statements related to events and warnings in the context of application logging

Log messages (info, warn, debug)

logging information debug warn

No Comments

No Known Activations