INDEX

Explanations

specific nouns and articles related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 VizieR

-0.51

 Ramírez

-0.51

 Barbier

-0.50

 persoons

-0.50

 Ramirez

-0.48

примеча

-0.48

éclairage

-0.48

 Nieto

-0.47

an

-0.46

 Barber

-0.45

POSITIVE LOGITS

WriteTagHelper

0.59

tagext

0.58

TestingModule

0.56

 OMITBAD

0.56

AISSEE

0.56

GOTREF

0.54

StoryboardSegue

0.54

featureID

0.52

CodedInputStream

0.52

abestanden

0.51

Activations Density 1.255%

specific nouns and articles related to various topics

No Comments

No Known Activations