INDEX

Explanations

terms or phrases related to user interface elements and button interactions

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

 épaules

-0.78

 vérit

-0.76

 pouvoirs

-0.74

 lèvres

-0.74

 négociations

-0.71

 vœux

-0.71

 gouvernements

-0.70

 boî

-0.68

 leçons

-0.67

 genoux

-0.66

POSITIVE LOGITS

 these

0.72

these

0.65

tols

0.63

 sánh

0.61

 those

0.60

 theses

0.60

iths

0.59

nessed

0.58

leps

0.57

dities

0.57

Activations Density 0.771%

terms or phrases related to user interface elements and button interactions

No Comments

No Known Activations