INDEX

Explanations

references to physical space and its dimensions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

AndEndTag

-0.38

Aktualisiert

-0.35

 referrerpolicy

-0.34

 VIDEOT

-0.33

SetBool

-0.33

scriptcase

-0.32

şört

-0.32

 viewWillAppear

-0.31

結果は

-0.31

<tfoot>

-0.31

POSITIVE LOGITS

 space

3.45

space

2.91

 Space

2.73

 SPACE

2.69

Space

2.67

 spaces

2.52

 espacio

2.50

SPACE

2.44

 espaço

2.38

空间

2.30

Activations Density 0.151%

references to physical space and its dimensions

No Comments

No Known Activations