INDEX

Explanations

cooking instructions and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

://$

-0.51

ReusableCell

-0.50

gab

-0.42

duct

-0.42

醛

-0.41

layan

-0.41

posição

-0.41

 propOrder

-0.40

метры

-0.40

Dy

-0.40

POSITIVE LOGITS

AndEndTag

0.66

queryInterface

0.64

 evenly

0.63

Hentet

0.61

 arany

0.60

Toponymie

0.60

脚注の使い方

0.59

Бахар

0.59

}\]

0.58

 visibly

0.58

Activations Density 0.132%

cooking instructions and processes

No Comments

No Known Activations