INDEX

Explanations

specific quantitative measurements and estimates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 przecież

-0.45

Cyfeiriadau

-0.40

:✨

-0.39

ďaka

-0.38

Nested

-0.37

 pourtant

-0.37

even

-0.36

 дори

-0.36

 dessutom

-0.33

POSITIVE LOGITS

 ungefähr

0.84

 approximately

0.83

 Approximately

0.79

 aproximadamente

0.77

 approximate

0.77

 approx

0.77

 roughly

0.74

 aproximativ

0.74

 ongeveer

0.74

approximately

0.74

Activations Density 0.416%

specific quantitative measurements and estimates

No Comments

No Known Activations