INDEX

Explanations

numerical values and references to statistical data

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

 ujednoznacz

-0.56

RectangleBorder

-0.52

henswürdigkeiten

-0.51



-0.50

VYMaps

-0.44

 فريبيس

-0.44

 fieldName

-0.41

ennung

-0.41

 unknownFields

-0.40

 Occidente

-0.40

POSITIVE LOGITS

ſelf

0.44

 Shrewsbury

0.44

smarty

0.44

 diría

0.42

 chup

0.41

出版年

0.41

spline

0.41

whip

0.41

delivery

0.40

gång

0.40

Activations Density 0.850%

numerical values and references to statistical data

No Comments

No Known Activations