INDEX

Explanations

terms related to innovation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.58

-0.55

get

-0.55

-0.54

es

-0.54

Kes

-0.53

-0.51

غراف

-0.50

POSITIVE LOGITS

Innov

1.47

 innovate

1.45

 innov

1.41

 innovation

1.41

 INNOV

1.40

 innovations

1.40

innov

1.39

Innovation

1.38

 Innovation

1.34

innovation

1.33

Activations Density 0.067%

terms related to innovation

No Comments

No Known Activations