INDEX

Explanations

references to academic roles and educational programs

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

Words/tokens appearing before course names or academic subjects

np_acts-logits-general · gemini-2.0-flash

academic classes and subjects

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ksin

-0.39

chad

-0.39

CreateModel

-0.38

 simb

-0.38

lach

-0.37

oria

-0.36

latego

-0.36

vimeo

-0.35

ліз

-0.35

setCancelable

-0.35

POSITIVE LOGITS

PyExc

0.77

jsxFileName

0.75

 estekak

0.75

<?

0.73

IUrlHelper

0.73

 wireType

0.73

CWE

0.72

 Italijanski

0.72

Introductory

0.71

featureID

0.70

Activations Density 0.111%

references to academic roles and educational programs

Words/tokens appearing before course names or academic subjects

academic classes and subjects

No Comments

No Known Activations