INDEX

Explanations

references to products and their performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 ujednoznacz

-0.57

 ब्रेकडाउन

-0.56

CrossRef

-0.54

ParallelGroup

-0.52

adaptiveStyles

-0.51

KommentareTeilen

-0.50

WebElementEntity

-0.49

printStackTrace

-0.48

aktur

-0.47

AccessorTable

-0.47

POSITIVE LOGITS

:✨

0.46

apimachinery

0.39

Sel

0.37

 raiſ

0.37

 OMITBAD

0.35

 Delf

0.34

timbangkan

0.34

 ſta

0.34

 ſte

0.33

RTLR

0.33

Activations Density 0.767%

references to products and their performance metrics

No Comments

No Known Activations