INDEX

Explanations

mathematical and statistical terminology related to decision theory and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nakalista

-1.03

 Administrativna

-0.98

 AssemblyCulture

-0.95

⅘

-0.76

########.

-0.71

windowFixed

-0.71

 Taktlose

-0.70

EDEFAULT

-0.67

WriteAttribute

-0.67

MessageOf

-0.64

POSITIVE LOGITS

ViewFeatures

0.45

ScopeManager

0.35

RunWith

0.33

 célèbre

0.31

ثيق

0.31

JScrollPane

0.31

 ComVisible

0.30

 gén

0.30

principalTable

0.30

Brainz

0.30

Activations Density 13.335%

mathematical and statistical terminology related to decision theory and functions

No Comments

No Known Activations