INDEX

Explanations

references to usage, application, or implementation of items and concepts in various contexts

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

Prepositions following a specific word

np_acts-logits-general · gemini-2.0-flash

use carefully

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

LookAnd

-0.89

出版年

-0.74

saraba

-0.69

StructEnd

-0.67

 kasarigan

-0.66

ReusableCell

-0.65

WriteTagHelper

-0.63

__(/*!

-0.63

 nahilalakip

-0.62

 meille

-0.59

POSITIVE LOGITS

 sparingly

0.86

 wisely

0.72

 interchangeably

0.68

 instead

0.66

ในการ

0.64

instead

0.60

 extensively

0.59

 judic

0.53

enumii

0.53

 liberally

0.53

Activations Density 0.563%

references to usage, application, or implementation of items and concepts in various contexts

Prepositions following a specific word

use carefully

No Comments

No Known Activations