INDEX

Explanations

words related to names and their meanings, particularly from different languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 myſelf

-0.74

WithIOException

-0.63

 poffible

-0.63

 Monfieur

-0.59

expandindo

-0.59

formik

-0.59

 Conſ

-0.59

 Jefus

-0.58

 Majefty

-0.58

 greateſt

-0.57

POSITIVE LOGITS

 propOrder

0.58

Datuak

0.55

 neutre

0.55

wpi

0.55

 ویکی‌پدیای

0.53

 translating

0.53

 означа

0.53

 PARSER

0.53

 Sanskrit

0.53

 unknownFields

0.53

Activations Density 0.106%

words related to names and their meanings, particularly from different languages

No Comments

No Known Activations