INDEX

Explanations

URLs and references to online resources or tools

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

存于互联网档案馆

-0.56

 pouvoit

-0.51

,:);

-0.50

 Wiktionnaire

-0.47

 trekken

-0.45

enderror

-0.45

 MonoBehaviour

-0.45

 nadzieję

-0.44

 Савезне

-0.44

 zupeł

-0.43

POSITIVE LOGITS

träger

0.44

 propOrder

0.41

ContentAsync

0.40

Styleable

0.40

 optimise

0.40

Ion

0.38

Попис

0.38

质

0.36

Jou

0.35

scheid

0.34

Activations Density 0.231%

URLs and references to online resources or tools

No Comments

No Known Activations