INDEX

Explanations

terms related to continuity and mathematical proofs

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

 للمعارف

-0.99

endpush

-0.88

hydrates

-0.83

printStackTrace

-0.80

+:+

-0.78

bicara

-0.77

Gom

-0.74

 éché

-0.73

HomeAsUpEnabled

-0.73

 Curie

-0.72

POSITIVE LOGITS

 Thorpe

0.94

 Tobias

0.84

Tobias

0.79

UOUS

0.79

 Slade

0.77

 prove

0.75

 proof

0.74

Genius

0.71

 relief

0.70

 Jolly

0.69

Activations Density 0.752%

terms related to continuity and mathematical proofs

No Comments

No Known Activations