INDEX

Explanations

questions and phrases indicating uncertainty or inquiry

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

 himo

-0.66

 صوتيه

-0.64

PhysRevLett

-0.63

 sentiers

-0.60

 soggetto

-0.59

IUrlHelper

-0.59

 habet

-0.59

 amitié

-0.58

GeneratedMessage

-0.57

anet

-0.57

POSITIVE LOGITS

<?

0.60

poons

0.60

 GoogleFonts

0.58

 henvisninger

0.57

omiast

0.56

 createSprite

0.55

HasForeignKey

0.55

TDG

0.53

withIdentifier

0.53

)];

0.52

Activations Density 0.082%

questions and phrases indicating uncertainty or inquiry

No Comments

No Known Activations