INDEX

Explanations

code constructs and programming terminology related to functions and classes

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

Code snippets, especially class/type definitions

np_acts-logits-general · gemini-2.0-flash

code, class names, and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

TokenNameLPAREN

-0.36

ggiata

-0.35

webElementXpaths

-0.35

AdapterView

-0.34

StoryboardSegue

-0.34

SurfaceView

-0.32

 ayak

-0.32

 vorder

-0.31

findpost

-0.31

 kedua

-0.30

POSITIVE LOGITS

 useful

0.50

Хьажоргаш

0.49

 ubiquitous

0.49

InjectAttribute

0.49

常用的

0.48

 pows

0.48

IUrlHelper

0.47

通用

0.47

antaranya

0.46

ſelves

0.46

Activations Density 0.585%

code constructs and programming terminology related to functions and classes

Code snippets, especially class/type definitions

code, class names, and definitions

No Comments

No Known Activations