INDEX

Explanations

phrases related to employing methods or searching for conditions in a mathematical or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 الحره

-0.85

 >=",

-0.77

continence

-0.76

TintMode

-0.76

انيف

-0.74

}\]

-0.71

новниш

-0.71

noons

-0.69

ganj

-0.68

inafter

-0.68

POSITIVE LOGITS

 fácilmente

0.80

can

0.74

 facilmente

0.73

 facilement

0.67

 easily

0.65

bitField

0.59

can

0.58

媲

0.57

 safely

0.57

Can

0.56

Activations Density 1.166%

phrases related to employing methods or searching for conditions in a mathematical or technical context

No Comments

No Known Activations