INDEX

Explanations

rankings and positions in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

strich

-0.46

moet

-0.41

 STAND

-0.41

نم

-0.40

:✨

-0.40

 experimentation

-0.39

 Lips

-0.39

nuk

-0.38

Bun

-0.38

 experiment

-0.38

POSITIVE LOGITS

 propOrder

0.59

parsedMessage

0.51

idenav

0.47

featureID

0.47

OGND

0.47

tanleria

0.45

----</

0.44

addContainerGap

0.42

invokeLater

0.41

Activations Density 0.560%

rankings and positions in competitive contexts

No Comments

No Known Activations