INDEX

Explanations

metrics and statistics related to diagnostic tests and their performance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GraphicsUnit

-0.55

Manbalar

-0.54

Portale

-0.52

addCriterion

-0.51

vode

-0.50

RTLD

-0.50

ThroughAttribute

-0.49

 utafitiHapana

-0.49

 pere

-0.48

reportWebVitals

-0.47

POSITIVE LOGITS

IntoConstraints

0.68

awtextra

0.66

hyrchwyd

0.55

 StatefulWidget

0.55

theless

0.53

ρίς

0.53

ীব

0.51

 accedi

0.51

 referenties

0.50

=.

0.50

Activations Density 0.506%

metrics and statistics related to diagnostic tests and their performance

No Comments

No Known Activations