INDEX

Explanations

phrases indicating initial conditions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

rungsseite

-0.98

adaptiveStyles

-0.89

EDEFAULT

-0.88

 EconPapers

-0.81

oredCriteria

-0.80

 Normdatei

-0.80

 lenker

-0.78

OGND

-0.76

 виправивши

-0.76

 estekak

-0.75

POSITIVE LOGITS

 initial

1.11

Initial

0.91

 initially

0.87

 iniciales

0.86

initial

0.82

 initiale

0.81

 Initial

0.75

 inicialmente

0.73

 iniziale

0.65

 semula

0.64

Activations Density 0.476%

phrases indicating initial conditions or states

No Comments

No Known Activations