INDEX

Explanations

expressions related to riding and vehicles

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

about riding

np_acts-logits-general · gemini-2.0-flash

forms of ride

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

 AssemblyCulture

-0.80

WriteTagHelper

-0.78

脚注の使い方

-0.65

-*-

-0.58

ebab

-0.56

omiast

-0.55

 Provence

-0.52

 Normdatei

-0.52

 feldspar

-0.52

érard

-0.51

POSITIVE LOGITS

 rides

1.12

 Rides

0.98

 riders

0.89

 ride

0.88

 Riding

0.87

 rode

0.86

 riding

0.86

 RIDE

0.84

 Rider

0.83

 rider

0.83

Activations Density 0.045%

expressions related to riding and vehicles

about riding

forms of ride

No Comments

No Known Activations