INDEX

Explanations

mathematical notation related to sets and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

onViewCreated

-0.72

 pleaſure

-0.71

 poffible

-0.67

 ſtand

-0.61

 fevere

-0.59

 leaſt

-0.58

ſelves

-0.58

 poffe

-0.56

 beſt

-0.56

 neceff

-0.56

POSITIVE LOGITS

Portail

0.77

AndEndTag

0.65

Демографія

0.62

writeField

0.62

fpm

0.61

colhead

0.59

λίου

0.59

жнему

0.59

EReference

0.57

elemField

0.57

Activations Density 0.503%

mathematical notation related to sets and their properties

No Comments

No Known Activations