INDEX

Explanations

elements related to programming instructions and method definitions

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

Followed by assignment operators

np_acts-logits-general · gemini-2.0-flash

code structure and types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 обла

-0.39

 granddaughter

-0.39

ving

-0.38

 setTotal

-0.38

<0xB4>

-0.37

 synt

-0.37

bearing

-0.36

 grandson

-0.36

ồ

-0.36

esistenza

-0.36

POSITIVE LOGITS

 CreateTagHelper

1.05

 pinulongan

0.96

DockStyle

0.91

bootstrapcdn

0.88

+#+#

0.85

AnimationsModule

0.83

 resourceCulture

0.83

fromnode

0.80

routeProvider

0.79

 ModelExpression

0.79

Activations Density 0.430%

elements related to programming instructions and method definitions

Followed by assignment operators

code structure and types

No Comments

No Known Activations