INDEX

Explanations

phrases and concepts associated with ideas and thoughts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

</em>

-0.70

roff

-0.60

quiv

-0.58

 Muñoz

-0.57

 Marte

-0.56

ன்ன

-0.56

*/

-0.56

ingual

-0.56

ç

-0.56

 Cerv

-0.55

POSITIVE LOGITS

 IDEA

1.81

 ideas

1.80

Idea

1.74

 Ideas

1.72

ideas

1.68

Ideas

1.67

 Idea

1.67

IDEA

1.59

 IDEAS

1.57

idea

1.49

Activations Density 0.036%

phrases and concepts associated with ideas and thoughts

No Comments

No Known Activations