INDEX

Explanations

phrases related to coding and programming tasks, particularly those involving writing scripts or queries

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

writing code or scripts

np_acts-logits-general · gemini-2.0-flash

writing code or functions

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

 незавершена

-0.79

 يتيمه

-0.73

 BorderRadius

-0.59

MemoryWarning

-0.58

IMPORTED

-0.58

UnknownFields

-0.57

 autorytatywna

-0.57

featureID

-0.55

Clik

-0.53

helf

-0.52

POSITIVE LOGITS

 code

2.12

code

1.69

代码

1.61

 software

1.59

 Code

1.49

 codes

1.48

 program

1.47

Code

1.43

 código

1.42

 코드

1.41

Activations Density 1.350%

phrases related to coding and programming tasks, particularly those involving writing scripts or queries

writing code or scripts

writing code or functions

No Comments

No Known Activations