INDEX

Explanations

references to news organizations and sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

achelor

-0.50

oubliez

-0.48

ngdoc

-0.48

mu

-0.47

 treat

-0.46

-0.45

 IActionResult

-0.42

ɹ

-0.41

Ear

-0.41

-0.40

POSITIVE LOGITS

UTERS

1.21

 Reuters

0.91

PRNewswire

0.89

Reuters

0.86

aarrggbb

0.86

ThroughAttribute

0.85

 reuters

0.85

 químicas

0.79

REUTERS

0.78

 متعلقه

0.78

Activations Density 0.057%

references to news organizations and sources

No Comments

No Known Activations