INDEX

Explanations

code constructs and programming-related terminology

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

Code parsing and variable assignment

np_acts-logits-general · gemini-2.0-flash

function calls and definitions

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

 userList

-0.68

 Comprometido

-0.64

 newList

-0.63

 pageNo

-0.61

 maxSize

-0.61

 mList

-0.61

 isSelected

-0.61

 JpaRepository

-0.60

 isSuccess

-0.59

 currentValue

-0.59

POSITIVE LOGITS

 generate

1.18

 make

1.14

 create

1.13

get

1.11

 build

1.09

 prepare

1.07

generate

1.06

 calculate

1.02

create

1.00

make

0.98

Activations Density 0.336%

code constructs and programming-related terminology

Code parsing and variable assignment

function calls and definitions

No Comments

No Known Activations