INDEX

Explanations

symbols and annotations commonly used in programming or scripting languages

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

发表于

-0.54

$_['

-0.50

הערות

-0.48

 ujednoznacz

-0.46

 disambiguazione

-0.45

__(/*!

-0.45

chartInstance

-0.44

-------------</

-0.44

----</

-0.40

Pranala

-0.39

POSITIVE LOGITS

+#+#

1.05

 ſch

0.46

RefNanny

0.46

 مفص

0.45

 ſche

0.44

 nahilalakip

0.43

 avoient

0.42

 Infórmanos

0.42

AxisAlignment

0.41

 BorderRadius

0.40

Activations Density 0.486%

symbols and annotations commonly used in programming or scripting languages

No Comments

No Known Activations