INDEX

Explanations

physical attributes measured in terms of height and weight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.56

bile

-0.51

-0.48

-0.46

mère

-0.44

ida

-0.43

 tapa

-0.43

-0.42

 insgesamt

-0.42

grandmother

-0.41

POSITIVE LOGITS

 tall

1.01

 taller

1.01

 tallest

0.97

 height

0.95

IntoConstraints

0.95

 defaultstate

0.91

thâu

0.89

makeConstraints

0.86

tall

0.85

 HEIGHT

0.84

Activations Density 0.081%

physical attributes measured in terms of height and weight

No Comments

No Known Activations