INDEX

Explanations

terms related to height comparisons and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ÉR

-0.46

Gra

-0.46

Ul

-0.45

opan

-0.43

UGAL

-0.42

Mode

-0.42

judice

-0.41

addCriterion

-0.40

Референце

-0.40

ấu

-0.40

POSITIVE LOGITS

 size

1.44

 length

1.27

 height

1.14

size

1.12

 lenght

1.07

 width

1.06

 sizes

1.04

 SIZE

1.01

length

0.95

 thickness

0.95

Activations Density 0.485%

terms related to height comparisons and quantities

No Comments

No Known Activations