INDEX

Explanations

terms related to measurements and performance assessment in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Bescheid

-0.48

-0.46

+#+#

-0.46

 when

-0.44

✷

-0.43

 autorytatywna

-0.42

 Entfer

-0.41

 failing

-0.41

 culturelles

-0.41

POSITIVE LOGITS

consulté

0.78

 exists

0.73

 occurred

0.71

 ensued

0.71

 existed

0.71

istoitu

0.70

zarchiwizowane

0.69

 GoogleFonts

0.67

 Audiodateien

0.65

verwijspagina

0.64

Activations Density 1.074%

terms related to measurements and performance assessment in scientific contexts

No Comments

No Known Activations