INDEX

Explanations

brand-related terms, especially those indicating novelty or newness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

τά

-0.42

再び

-0.39

attan

-0.38

another

-0.36

by

-0.36

multi

-0.36

uns

-0.36

ten

-0.35

 particular

-0.35

 Another

-0.35

POSITIVE LOGITS

 ostavi

0.99

+#+

0.96

KommentareTeilen

0.95

########.

0.94

 StatefulWidget

0.91

脚注の使い方

0.87

 AspNetCore

0.86

 BoxFit

0.83

 Мексичка

0.82

 financières

0.81

Activations Density 0.086%

brand-related terms, especially those indicating novelty or newness

No Comments

No Known Activations

brand-related terms, especially those indicating novelty or newness

No Comments

No Known Activations