INDEX

Explanations

elements related to protobuf message definitions and structure

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

Protobuf-related code generation

np_acts-logits-general · gemini-2.0-flash

protobuf message definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

principalColumn

-0.74

aspectj

-0.64

 localObject

-0.61

ANSI

-0.59

 محفوظة

-0.58

URLException

-0.57

AsUp

-0.54

BASEPATH

-0.53

xaml

-0.53

bpy

-0.53

POSITIVE LOGITS

google

0.61

 proto

0.61

protobuf

0.57

protoc

0.56

 google

0.55

proto

0.54

GOOGLE

0.53

 GOOGLE

0.53

pb

0.52

 protobuf

0.49

Activations Density 0.542%

elements related to protobuf message definitions and structure

Protobuf-related code generation

protobuf message definitions

No Comments

No Known Activations