INDEX

Explanations

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Arora

-0.86

 Lawson

-0.82

 propOrder

-0.82

 թվական

-0.78

Pag

-0.78

 Italijani

-0.74

 Berger

-0.73

 Katz

-0.73

Rij

-0.73

INCREF

-0.72

POSITIVE LOGITS

 Coch

1.05

 Recep

0.95

 Ralf

0.92

 Schlu

0.89

 myſelf

0.88

 Jefus

0.87

 purpoſe

0.87

 Plaid

0.84

 pleaſure

0.83

 Schalke

0.82

Activations Density 2.287%

proper nouns and names

No Comments

No Known Activations