INDEX

Explanations

elements of utility or user experience regarding software or systems

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

Code-related discussions

np_acts-logits-general · gemini-2.0-flash

expressing states or actions

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

 Anda

-0.66

 bedoeld

-0.61

 hinaus

-0.61

 있습니다

-0.60

woordig

-0.56

而来

-0.56

 Himmel

-0.56

二是

-0.55

dders

-0.55

 tiež

-0.55

POSITIVE LOGITS

DataAnnotations

0.71

RenderAtEndOf

0.70

tvguidetime

0.61

 propOrder

0.58

 kaynağından

0.57

 JAXB

0.55

 AssemblyCulture

0.53

 AssemblyVersion

0.52

::$_

0.52

 typelib

0.49

Activations Density 0.051%

elements of utility or user experience regarding software or systems

Code-related discussions

expressing states or actions

No Comments

No Known Activations