INDEX

Explanations

statements related to risks or warnings associated with health and safety

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

FormTagHelper

-0.50

ત્ર

-0.49

vader

-0.48

 Zinn

-0.47

 NSCoder

-0.45

 suggestion

-0.45

 perla

-0.45

 consejo

-0.45

тику

-0.45

 syno

-0.44

POSITIVE LOGITS

argout

0.67

 AssemblyTitle

0.65

KURZBESCHREIBUNG

0.64

bidities

0.62

énario

0.60

zzleHttp

0.59

égration

0.57

 podjela

0.56

scarpe

0.55

 kilowatt

0.55

Activations Density 0.124%

statements related to risks or warnings associated with health and safety

No Comments

No Known Activations