INDEX

Explanations

specific technical terms, particularly in scientific or mathematical contexts

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

↵↵

-0.42

point

-0.37

 point

-0.37

sf

-0.36

-0.35

El

-0.35

top

-0.33

EndPoint

-0.33

end

-0.33

POSITIVE LOGITS

ConstraintMaker

0.96

IntoConstraints

0.91

:✨

0.82

AndEndTag

0.81

 ModelExpression

0.79

rungsseite

0.76

WithIOException

0.75

 pinulongan

0.75

 initComponents

0.75

 onOptions

0.73

Activations Density 3.724%

specific technical terms, particularly in scientific or mathematical contexts

No Comments

No Known Activations