INDEX

Explanations

references to specific biochemical terms or abbreviations related to a particular treatment or study involving AT

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

expandindo

-0.73

ROE

-0.66

windowFixed

-0.62

DMG

-0.59

 ویکی‌پدی

-0.58

SOO

-0.57

ⓧ

-0.57

AddHtmlAttribute

-0.57

الإنجليزية

-0.56

dof

-0.55

POSITIVE LOGITS

AT

1.51

BT

1.25

BT

1.22

PT

1.12

AT

1.10

PT

1.08

GT

1.03

DT

1.03

DT

1.02

MT

1.02

Activations Density 0.176%

references to specific biochemical terms or abbreviations related to a particular treatment or study involving AT

No Comments

No Known Activations