INDEX

Explanations

references to the concept of being "loose."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

sizeCache

-0.82

XmlAccessType

-0.69

TestingModule

-0.63

Siv

-0.63

theless

-0.63

ActionResult

-0.61

Nevertheless

-0.60

 unfavourable

-0.59

 repercussions

-0.59

 endfor

-0.59

POSITIVE LOGITS

 loose

0.80

 оригіналу

0.76

 Loose

0.75

Loose

0.70

loose

0.68

 LEFT

0.63

 leave

0.63

 continuously

0.62

 courtesy

0.62

左側

0.61

Activations Density 0.069%

references to the concept of being "loose."

No Comments

No Known Activations