INDEX

Explanations

terminology related to performance metrics and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 محفوظة

-0.72

contentLoaded

-0.59

MENAFN

-0.52

+:+

-0.52

Hauptartikel

-0.51

 שוליים

-0.50

 JpaRepository

-0.50

encodeWith

-0.48

fromnode

-0.47

tvguidetime

-0.47

POSITIVE LOGITS

unknownFields

0.71

EndGlobalSection

0.71

 CreateTagHelper

0.71

 hundred

0.69

 eighty

0.60

 Ninety

0.59

hundred

0.59

 HUND

0.56

几十

0.56

Fifty

0.55

Activations Density 0.539%

terminology related to performance metrics and evaluations

No Comments

No Known Activations