INDEX

Explanations

references to writing and literary activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

ReusableCell

-0.53

ConstraintMaker

-0.51

ustimmung

-0.51

UnusedPrivate

-0.47

 <>",

-0.47

 AssemblyTitle

-0.46

principalColumn

-0.45

makeConstraints

-0.43

apunov

-0.43

ukunft

-0.43

POSITIVE LOGITS

 readers

1.60

 literary

1.54

 reader

1.50

 authors

1.48

 Readers

1.44

 writers

1.42

 author

1.38

Readers

1.33

 writer

1.32

 Writers

1.32

Activations Density 0.884%

references to writing and literary activities

No Comments

No Known Activations