INDEX

Explanations

statistics related to performance metrics and health outcomes

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

INCREF

-0.49

kuuta

-0.49

 boost

-0.48

Beweg

-0.46

nthetic

-0.45

 quoi

-0.44

 boosts

-0.44

 sufficiente

-0.43

 sapat

-0.43

rophoresis

-0.43

POSITIVE LOGITS

setVerticalGroup

0.68

 reduction

0.65

getDoctrine

0.64

Reducing

0.62

 Reducing

0.61

 udaler

0.60

EndContext

0.59

 Reduction

0.58

 incurred

0.58

zero

0.57

Activations Density 0.684%

statistics related to performance metrics and health outcomes

No Comments

No Known Activations