INDEX

Explanations

technical terms related to engine performance and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

InvalidProtocol

-0.70

mergeFrom

-0.64

 يونيو

-0.51

uttavia

-0.47

olving

-0.47

STATION

-0.47

 station

-0.46

xito

-0.46

 أبريل

-0.45

NotNil

-0.44

POSITIVE LOGITS

EnableWeb

0.64

 muffler

0.62

 lenker

0.61

ftagPool

0.60

chappement

0.60

ljen

0.60

 <<<<<<<<<<<<<<

0.59

hyrchwyd

0.58

 виправивши

0.58

 OFDb

0.57

Activations Density 0.681%

technical terms related to engine performance and components

No Comments

No Known Activations