INDEX

Explanations

questions about 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 محفوظة

-0.57

bru

-0.53

цов

-0.52

istock

-0.51

anin

-0.50

An

-0.50

<eos>

-0.49

quist

-0.49

wo

-0.48

asar

-0.48

POSITIVE LOGITS

Efq

0.97

 itſelf

0.89

 houſe

0.88

 Monfieur

0.86

 purpoſe

0.85

 faſt

0.85

 Jefus

0.84

 виправивши

0.83

 leſs

0.83

 Houſe

0.83

Activations Density 0.197%

questions about quantities and measurements

No Comments

No Known Activations