INDEX

Explanations

references to specific documents and their details

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

demonstrative preceding document type

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

ValueStyle

-0.90

Portale

-0.64

tagHelperRunner

-0.63

 awakeFromNib

-0.63

SequentialGroup

-0.63

expandindo

-0.62

Portail

-0.61

MessageWindow

-0.60

GEBURTSDATUM

-0.59

SharedCtor

-0.58

POSITIVE LOGITS

 document

0.77

 article

0.68

 published

0.60

 publication

0.60

 report

0.60

 written

0.58

 informative

0.58

 című

0.56

 documento

0.52

document

0.51

Activations Density 0.065%

references to specific documents and their details

demonstrative preceding document type

No Comments

No Known Activations