INDEX

Explanations

proper nouns, particularly names and titles associated with individuals and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

GEBURTSDATUM

-0.97

rungsseite

-0.79

ⓧ

-0.78

 Roskov

-0.73

onomía

-0.72

EDEFAULT

-0.72

 незавершена

-0.69

liothèque

-0.69

 protoimpl

-0.67

Rüyada

-0.67

POSITIVE LOGITS

 myſelf

0.98

 purpoſe

0.94

 pleaſure

0.94

Efq

0.94

 itſelf

0.93

 uſed

0.91

 ſte

0.91

 Anſ

0.91

 Monfieur

0.90

 ſta

0.89

Activations Density 2.930%

proper nouns, particularly names and titles associated with individuals and organizations

No Comments

No Known Activations