INDEX

Explanations

references to the term "AP" and related acronyms in scientific and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 autorytatywna

-0.71

sträger

-0.54

Viitteet

-0.52

AutoField

-0.50

ClientSize

-0.48

collapsible

-0.47

thenReturn

-0.46

Rod

-0.46

roglo

-0.46

POSITIVE LOGITS

FAP

0.97

APL

0.96

Aps

0.95

APE

0.94

APD

0.90

APM

0.89

 Majefty

0.89

APS

0.87

 Monfieur

0.84

APO

0.83

Activations Density 0.234%

references to the term "AP" and related acronyms in scientific and technical contexts

No Comments

No Known Activations