INDEX

Explanations

specific interactions and status updates related to programming and web development processes

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

Actions that happen automatically

np_acts-logits-general · gemini-2.0-flash

automatic actions

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

awtextra

-0.62

matchCondition

-0.54

GeneratedCode

-0.54

出版年

-0.52

 protoimpl

-0.50

Especially

-0.50

InstanceState

-0.50

pragma

-0.49

 combineReducers

-0.48

+#+

-0.47

POSITIVE LOGITS

 automatically

1.22

automatically

0.86

 automaticamente

0.85

 automatiquement

0.83

 automatisch

0.82

 Automatically

0.81

 automatic

0.77

 default

0.77

 AUTOMATIC

0.77

 automáticamente

0.74

Activations Density 1.001%

specific interactions and status updates related to programming and web development processes

Actions that happen automatically

automatic actions

No Comments

No Known Activations