INDEX

Explanations

references to statistical measures or complex methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

studio

-0.44

=@"

-0.42

station

-0.40

regular

-0.38

shortcut

-0.37

THY

-0.37

viewer

-0.37

utnik

-0.37

REGULAR

-0.37

protocols

-0.36

POSITIVE LOGITS

 measure

0.69

RectangleBorder

0.68

 Measure

0.66

eval

0.65

measure

0.59

 MEASURE

0.58

Measure

0.58

DockStyle

0.57

 ब्रेकडाउन

0.56

 compleja

0.55

Activations Density 0.137%

references to statistical measures or complex methodologies

No Comments

No Known Activations