INDEX

Explanations

programming-related documentation and code structures

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

Code, database, or model related terminology

np_acts-logits-general · gemini-2.0-flash

entity models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.67

ArgumentParser

-0.59

ंदीखरीदारी

-0.57

########.

-0.56

 تانيه

-0.55

 Messina

-0.54

nė

-0.53

RectangleBorder

-0.52

舺

-0.52

 Controlling

-0.52

POSITIVE LOGITS

 model

0.80

 Model

0.74

Model

0.68

model

0.68

 models

0.64

モデル

0.62

模型

0.62

 모델

0.61

 MODEL

0.61

 relations

0.61

Activations Density 0.350%

programming-related documentation and code structures

Code, database, or model related terminology

entity models

No Comments

No Known Activations