INDEX

Explanations

specific locations, structures, and settings associated with various events and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.38.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

@"/

-0.42

 everywhere

-0.41

everywhere

-0.40

 Everywhere

-0.39

 überall

-0.38

 partout

-0.36

 везде

-0.35

 ovunque

-0.35

Everywhere

-0.34

pravy

-0.31

POSITIVE LOGITS

 owned

0.93

 located

0.90

 frequented

0.82

 belonging

0.81

 situated

0.81

owned

0.77

 inhabited

0.77

located

0.76

 occupied

0.75

 vacated

0.70

Activations Density 0.780%

specific locations, structures, and settings associated with various events and actions

No Comments

No Known Activations