INDEX

Explanations

mathematical notations and symbols used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

nos

-0.44

wat

-0.40

そうで

-0.37

timis

-0.37

ening

-0.37

 EDIT

-0.36

Hi

-0.35

na

-0.35

ate

-0.34

POSITIVE LOGITS

GEBURTSDATUM

0.94

 CreateTagHelper

0.94

 مشين

0.90

abestanden

0.89

ReusableCell

0.87

ंदीखरीदारी

0.87

rrggbb

0.87

ResumeLayout

0.87

}{@

0.85

GEBURTS

0.85

Activations Density 0.262%

mathematical notations and symbols used in equations

No Comments

No Known Activations