INDEX

Explanations

formatted mathematical expressions and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

GraphicsUnit

-1.01

存于互联网档案馆

-1.01

 незавершена

-0.98



-0.92

ⓧ

-0.89

 صوتيه

-0.88

Personendaten

-0.87

MigrationBuilder

-0.84

 disambiguazione

-0.84

saraba

-0.83

POSITIVE LOGITS

міст

0.46

vedades

0.45

 reservados

0.45

...

0.45

tamment

0.44

 most

0.44

اشتی

0.43

 spesielt

0.43

0.42

Activations Density 0.443%

formatted mathematical expressions and symbols

No Comments

No Known Activations