INDEX

Explanations

phrases related to statistical analyses and research findings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 démocr

-0.53

 normaux

-0.52

 superiori

-0.52

 fondamentali

-0.51

 essenziale

-0.49

 franceses

-0.47

 Mutant

-0.47

 risol

-0.47

 giapp

-0.47

 carottes

-0.47

POSITIVE LOGITS

 multiple

0.85

 disambiguazione

0.82

 multi

0.81

]--;

0.67

multiple

0.66

 even

0.60

 reverse

0.60

non

0.60

PDOException

0.59

Enllaços

0.59

Activations Density 0.913%

phrases related to statistical analyses and research findings

No Comments

No Known Activations