INDEX

Explanations

keywords related to literary achievements and writing experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 either

-0.54

 scheduled

-0.51

กัน

-0.47

ávajú

-0.45

 comples

-0.45

 normally

-0.45

 guarn

-0.44

 corren

-0.44

 historique

-0.43

 Saison

-0.42

POSITIVE LOGITS

ArgsConstructor

0.94

 NSCoder

0.93

 EconPapers

0.85

complexContent

0.80

ScopeManager

0.79

BeginInit

0.72

Portály

0.72

KURZBESCHREIBUNG

0.70

AccessorTable

0.69

ThroughAttribute

0.69

Activations Density 0.296%

keywords related to literary achievements and writing experiences

No Comments

No Known Activations