INDEX

Explanations

descriptive phrases about suitability and effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

GEBURTSDATUM

-0.72

AndEndTag

-0.72

ValueStyle

-0.69

HasBeenSet

-0.64

Хьажоргаш

-0.63

 Biôgrafia

-0.62

IVEREF

-0.61

 Roskov

-0.59

lusconi

-0.59

Personendaten

-0.59

POSITIVE LOGITS

 ideal

2.57

 perfect

2.43

ideal

2.21

Ideal

2.13

 Ideal

2.10

perfect

2.09

 ideale

1.96

 suitable

1.96

Perfect

1.89

 Perfect

1.88

Activations Density 0.318%

descriptive phrases about suitability and effectiveness

No Comments

No Known Activations