INDEX

Explanations

references to numerical values and data representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

Derbyniad

-0.34

½

-0.32

เยอะ

-0.32

yatı

-0.31

bkz

-0.31

borderFill

-0.31

🍿

-0.31

consulté

-0.31

½

-0.30

İstinadlar

-0.30

POSITIVE LOGITS

0.61

0.58

0.57

0.56

0.55

BagConstraints

0.53

0.51

Activations Density 0.966%

references to numerical values and data representations

No Comments

No Known Activations