INDEX

Explanations

references to reading and continuing content

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

bootstrapcdn

-1.01

IVEREF

-0.84

GEBURTSDATUM

-0.83

IUrlHelper

-0.77

 AssemblyVersion

-0.77

LookAnd

-0.76

Personensuche

-0.73

ConstraintMaker

-0.73

featureID

-0.72

 ब्रेकडाउन

-0.72

POSITIVE LOGITS

devamını

0.62

...

0.42

Weiterlesen

0.37

»

0.36

»

0.35

 More

0.34

続きを読む

0.33

 Read

0.33

Read

0.32

More

0.30

Activations Density 0.263%

references to reading and continuing content

No Comments

No Known Activations