INDEX

Explanations

structured data operations and definitions

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

Code, paths, or database references

np_acts-logits-general · gemini-2.0-flash

technical documents

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

二是

-0.65

HBox

-0.59

这事

-0.57

vismo

-0.56

setLine

-0.56

 Nile

-0.53

IORS

-0.53

 cops

-0.52

 Aufs

-0.52

 Duomo

-0.52

POSITIVE LOGITS

RectangleBorder

0.79

原始内容存档于

0.76

 resourceCulture

0.74

TargetException

0.72

ApplicationTests

0.71

StreetMap

0.68

 ProtoMessage

0.66

IVEREF

0.65

 Мексичка

0.64

 المعيارى

0.64

Activations Density 0.879%

structured data operations and definitions

Code, paths, or database references

technical documents

No Comments

No Known Activations