INDEX

Explanations

coding structures and elements related to software configuration

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

Code, kubernetes, or YAML files

np_acts-logits-general · gemini-2.0-flash

type Pod

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

 onPostExecute

-0.69

oubliez

-0.57

 forgets

-0.56

 forgetting

-0.54

 palme

-0.51

 forget

-0.51

 Merrill

-0.50

>*/

-0.50

heses

-0.50

 Parry

-0.50

POSITIVE LOGITS

Pod

0.67

pod

0.62

Pod

0.61

 apie

0.56

 pods

0.52

pods

0.52

Pods

0.52

 Pods

0.52

 Cluster

0.51

POD

0.51

Activations Density 0.216%

coding structures and elements related to software configuration

Code, kubernetes, or YAML files

type Pod

No Comments

No Known Activations