INDEX

Explanations

references to numerical quantities and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 <<<<<<<<<<<<<<

-0.89

 ModelExpression

-0.77

wahlen

-0.68

 JAXB

-0.66

 Feathers

-0.61

+][

-0.60

GOTREF

-0.60

 незавершена

-0.59

of

-0.58

>[]

-0.57

POSITIVE LOGITS

 hvilken

0.63

 للمعارف

0.62

 icke

0.56

følgelig

0.56

 téléphonique

0.56

zeiti

0.56

 slutt

0.53

_-

0.53

 newly

0.52

icolon

0.52

Activations Density 0.312%

references to numerical quantities and measurements

No Comments

No Known Activations