INDEX

Explanations

sections of code or programming-related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

PROM

-0.47

ستان

-0.45

direktor

-0.44

género

-0.44

Geld

-0.43

ter

-0.42

הל

-0.42

Eval

-0.42

 cathe

-0.41

målet

-0.41

POSITIVE LOGITS

 تانيه

0.95

featureID

0.86

AndEndTag

0.84

 صوتيه

0.83

تقاوى

0.82

 EconPapers

0.81

uxxxx

0.80

+#+#

0.79

ISupport

0.77

GEBURTSDATUM

0.76

Activations Density 0.067%

sections of code or programming-related elements

No Comments

No Known Activations