INDEX

Explanations

terms associated with relaxation and comfort

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 виправивши

-0.84

+:+

-0.83

quelize

-0.77

PathVariable

-0.75

 CreateTagHelper

-0.73

{,

-0.73

 DbType

-0.73

amqp

-0.71

 &___

-0.71

 FormData

-0.70

POSITIVE LOGITS

 Relax

1.41

 relax

1.40

Relax

1.36

relax

1.34

 relaxed

1.30

 relaxing

1.26

 relaxation

1.22

relaxed

1.19

 Relaxed

1.18

 relaxes

1.17

Activations Density 0.095%

terms associated with relaxation and comfort

No Comments

No Known Activations