INDEX

Explanations

references to bearings or bearing systems in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 pinulongan

-0.90

didSet

-0.81

 AssemblyTitle

-0.81

 ddelweddau

-0.80

+#+#

-0.79

 quæ

-0.73

 BoxFit

-0.73

adeloupe

-0.71

ingtones

-0.71

хьтан

-0.70

POSITIVE LOGITS

 bearing

0.90

 Bearing

0.72

 bear

0.69

 players

0.68

Bearing

0.67

 BEAR

0.61

 bearings

0.60

 bore

0.59

 thrust

0.59

 Players

0.59

Activations Density 0.104%

references to bearings or bearing systems in various contexts

No Comments

No Known Activations