INDEX

Explanations

proper nouns and specific names related to individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Sucesor

-1.06

 snippetHide

-1.06

Hauptartikel

-1.03

awtextra

-1.03

ГЛА

-0.99

 }}"></

-0.98

 autorytatywna

-0.94

--}}

-0.93

"]).

-0.91

 beginnetje

-0.90

POSITIVE LOGITS

 Lubbock

0.77

 Greenwich

0.73

 Valenzuela

0.70

 harina

0.68

évaluateur

0.66

 vocale

0.65

 témoin

0.64

 Alvin

0.63

 Dhabi

0.62

Bop

0.61

Activations Density 9.226%

proper nouns and specific names related to individuals and entities

No Comments

No Known Activations