INDEX

Explanations

text related to "deck" and references to speech or dialogue

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

Efq

-0.72

SourceChecksum

-0.71

 Jefus

-0.69

AddTagHelper

-0.69

 disponibilités

-0.69

KommentareTeilen

-0.67

lardır

-0.67

 Theſe

-0.67

 quæ

-0.63

তথ্যসূত্র

-0.62

POSITIVE LOGITS

 deck

0.94

ja

0.88

 Deck

0.80

 Thrones

0.80

 decks

0.71

 Morin

0.68

bufio

0.65

 hobby

0.65

Deck

0.64

Tak

0.64

Activations Density 0.063%

text related to "deck" and references to speech or dialogue

No Comments

No Known Activations