INDEX

Explanations

parameters or elements associated with data definitions and configurations in programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

aski

-0.43

Ber

-0.38

gger

-0.38

endu

-0.35

 again

-0.35

 divis

-0.35

 spiked

-0.35

 politi

-0.34

not

-0.33

 medias

-0.33

POSITIVE LOGITS

oredCriteria

1.02

WithIOException

0.98

 Мексичка

0.97

出版年

0.96

 Roskov

0.94

IntoConstraints

0.93

 linkovi

0.92

 propOrder

0.92

 transfieras

0.92

saraba

0.91

Activations Density 0.476%

parameters or elements associated with data definitions and configurations in programming or data structures

No Comments

No Known Activations