INDEX

Explanations

references to statistical or regulatory elements related to organizational structures or processes

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

 ſche

-0.94

 myſelf

-0.82

 ſever

-0.81

 greateſt

-0.80

 Majefty

-0.80

ſelf

-0.79

 fevere

-0.78

 pleaſure

-0.75

 faſt

-0.75

 laſt

-0.75

POSITIVE LOGITS

use

0.94

 creation

0.83

 introduction

0.80

 establishment

0.78

 formation

0.77

 return

0.74

 release

0.72

 addition

0.68

 emergence

0.67

 presence

0.66

Activations Density 0.836%

references to statistical or regulatory elements related to organizational structures or processes

No Comments

No Known Activations