INDEX

Explanations

references to time durations measured in weeks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Füßen

-0.40

 ayudarte

-0.40

dafx

-0.38

 fyra

-0.37

åt

-0.36

 barnen

-0.36

 conmigo

-0.35

 testigos

-0.34

 exposiciones

-0.34

 juzgar

-0.34

POSITIVE LOGITS

OGND

0.81

المشاركات

0.65

 мәкал

0.59

 miner

0.58

 للاسماء

0.57

Rohy

0.56

 Miner

0.56

².

0.54

Demografie

0.52

 repr

0.51

Activations Density 0.470%

references to time durations measured in weeks

No Comments

No Known Activations