INDEX

Explanations

elements related to programming and data manipulation concepts in code

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

Followed by properties or attributes

np_acts-logits-general · gemini-2.0-flash

. followed by attribute/property

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IntoConstraints

-0.84

ANTLR

-0.53

исленность

-0.52

SerializedSize

-0.51

DeleteBehavior

-0.51

UnsafeEnabled

-0.49

:]:

-0.47

<eos>

-0.46

PageFactory

-0.46

glGen

-0.45

POSITIVE LOGITS

properties

0.79

 attributes

0.72

 properties

0.71

 nahilalakip

0.71

Properties

0.69

 lenker

0.65

getAttribute

0.65

 Attributes

0.64

 settings

0.63

Props

0.63

Activations Density 0.295%

elements related to programming and data manipulation concepts in code

Followed by properties or attributes

. followed by attribute/property

No Comments

No Known Activations