INDEX

Explanations

references to user information privacy and data handling

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

舺

-0.52

 فريبيس

-0.47

 poveznice

-0.45

 fieldNum

-0.44

 ويكيميديا

-0.41

 виправивши

-0.41

 kolor

-0.41

SequentialGroup

-0.40

expandindo

-0.40

SharedDtor

-0.39

POSITIVE LOGITS

 donors

0.46

 Recipients

0.43

 recipients

0.40

 Introduced

0.40

 introductions

0.40

parsedMessage

0.39

ordonnées

0.39

 sponsors

0.38

 Introdu

0.38

 Matching

0.38

Activations Density 0.415%

references to user information privacy and data handling

No Comments

No Known Activations