INDEX

Explanations

phrases related to historical discoveries and classifications in scientific contexts

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

Year followed by a name

np_acts-logits-general · gemini-2.0-flash

discovery and scientific publication

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

principalColumn

-0.63

 mxArray

-0.62

Personendaten

-0.60

endphp

-0.60

 snippetHide

-0.60

 autorytatywna

-0.58

 arşivlendi

-0.56

TagNumber

-0.54

 AssemblyVersion

-0.53

ConstraintMaker

-0.52

POSITIVE LOGITS

unic

0.49

提

0.43

discover

0.40

 discover

0.38

 discovered

0.37

URLConnection

0.36

annica

0.36

 giới

0.36

mbira

0.35

discovered

0.35

Activations Density 1.293%

phrases related to historical discoveries and classifications in scientific contexts

Year followed by a name

discovery and scientific publication

No Comments

No Known Activations