INDEX

Explanations

references to various types of entities, such as services, nutrients, drugs, genes, and elements

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

other categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

richTextPanel

-1.03

 CreateTagHelper

-1.02

évaluateur

-0.95

OGND

-0.86

webElementXpaths

-0.81

 propOrder

-0.80

PreferredItem

-0.80

AddTagHelper

-0.79

 otomatig

-0.79

 CURIAM

-0.78

POSITIVE LOGITS

 other

0.60

 others

0.53

 otros

0.51

 outros

0.48

 autres

0.45

others

0.44

 otras

0.44

 outras

0.44

 andere

0.43

 anderen

0.43

Activations Density 0.063%

references to various types of entities, such as services, nutrients, drugs, genes, and elements

other categories

No Comments

No Known Activations