INDEX

Explanations

specific measurements related to 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 @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

tric

-0.48

Beaucoup

-0.47

varna

-0.46

lots

-0.46

붕

-0.45

NAS

-0.43

heb

-0.42

'./

-0.41

 acceptance

-0.41

terly

-0.41

POSITIVE LOGITS

 tall

1.09

 height

1.08

 taller

1.05

 Height

1.02

 tallest

0.99

 Tall

0.99

IntoConstraints

0.97

tall

0.94

 TALL

0.91

height

0.89

Activations Density 0.151%

specific measurements related to height and weight

No Comments

No Known Activations