INDEX

Explanations

proper nouns and specific geographic or organizational entities

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

-0.36

ad

-0.35

 témoins

-0.35

-0.34

Impl

-0.33

Sevilla

-0.33

 vàng

-0.33

ელი

-0.33

 aberta

-0.32

ensaft

-0.32

POSITIVE LOGITS

expandindo

1.13

KommentareTeilen

1.00

脚注の使い方

0.96

 snippetHide

0.94

 дописавши

0.94

 kasarigan

0.93

 المعيارى

0.92

出版年

0.91

 مشين

0.91

 Савезне

0.90

Activations Density 2.670%

proper nouns and specific geographic or organizational entities

No Comments

No Known Activations