INDEX

Explanations

numerical identifiers or codes related to events or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ModelExpression

-0.68

InjectAttribute

-0.64

angliski

-0.58

 CreateTagHelper

-0.57

 otomatig

-0.54

makeConstraints

-0.53

 useStyles

-0.51

 disponibilités

-0.50

şiv

-0.49

 Италијани

-0.49

POSITIVE LOGITS

saraba

0.52

最快更新

0.51

 pinulongan

0.51

 NSCoder

0.50

Hauptartikel

0.49

Παραπομπές

0.47

IonicModule

0.46

nth

0.46

unt

0.46

BeginContext

0.45

Activations Density 0.172%

numerical identifiers or codes related to events or entities

No Comments

No Known Activations