INDEX

Explanations

questions and potential issues with processes or functionalities in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

こそ

-0.43

walde

-0.40

だからこそ

-0.40

才有

-0.38

 yourself

-0.37

 fijo

-0.37

 megsz

-0.36

bet

-0.36

ÈRE

-0.36

でしたね

-0.36

POSITIVE LOGITS

دانشنامهٔ

1.12

Personensuche

1.11

 esternos

1.03

脚注の使い方

1.02

 AssemblyCulture

0.92

jsxFileName

0.92

ScopeManager

0.88

SequentialGroup

0.88

DeleteBehavior

0.88

PreferredItem

0.87

Activations Density 0.436%

questions and potential issues with processes or functionalities in programming

No Comments

No Known Activations