INDEX

Explanations

references to types or categories of things

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

of its kind

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

RuleContext

-0.35

 Fudge

-0.33

卸载

-0.32

 Sander

-0.31

ComponentScan

-0.31

Kanpo

-0.31

𝟹

-0.31

żeli

-0.30

 patente

-0.30

án

-0.29

POSITIVE LOGITS

tagHelperRunner

0.81

webElementXpaths

0.74

 nahilalakip

0.68

 ligiloj

0.63

AsUp

0.61

gridx

0.57

ImageContext

0.54

 Савезне

0.54

 CreateTagHelper

0.53

Kind

0.52

Activations Density 0.007%

references to types or categories of things

of its kind

No Comments

No Known Activations