INDEX

Explanations

terms related to monitoring and evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 słucha

-0.49

 intptr

-0.48

 suprême

-0.44

esercito

-0.44

 współpracy

-0.43

 čier

-0.42

 przeznac

-0.41

explique

-0.41

 zwykle

-0.39

 téléph

-0.39

POSITIVE LOGITS

 pattern

0.90

 profile

0.83

spot

0.77

 plot

0.73

 profiles

0.72

yy

0.72

 patterns

0.69

 monitoring

0.67

pattern

0.65

 spot

0.63

Activations Density 0.641%

terms related to monitoring and evaluation processes

No Comments

No Known Activations