INDEX

Explanations

references to classification systems within scientific or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 resourceCulture

-0.97

🏽

-0.88

 AssemblyTitle

-0.88

🏿

-0.85

nezeu

-0.81

🏼

-0.79

🏾

-0.77

ьаж

-0.73

 withal

-0.73

 Faso

-0.72

POSITIVE LOGITS

 Class

1.16

 CLASS

1.11

 classes

1.08

Class

1.08

CLASS

0.99

 Classes

0.98

DriverManager

0.97

 class

0.97

classes

0.89

 clase

0.88

Activations Density 0.137%

references to classification systems within scientific or technical contexts

No Comments

No Known Activations