INDEX

Explanations

terms related to the application of scientific methods or principles

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

SourceChecksum

-0.93

zygous

-0.73

genheit

-0.71

 Cassini

-0.70

 AssemblyCulture

-0.68

 littéraire

-0.67

ьаж

-0.67

 possibilité

-0.66

hoeddwyd

-0.66

 aéreo

-0.66

POSITIVE LOGITS

 applied

2.47

 Applied

2.44

Applied

2.41

applied

2.25

 APPLIED

2.14

 Appl

1.48

 aplicada

1.37

 aplicado

1.34

Appl

1.14

 applic

0.98

Activations Density 0.175%

terms related to the application of scientific methods or principles

No Comments

No Known Activations