INDEX

Explanations

exclamatory phrases expressing surprise or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalColumn

-0.54

 ninguém

-0.51

 chiunque

-0.50

anmoins

-0.48

 délai

-0.48

 Jose

-0.48

ragt

-0.48

ocide

-0.46

 링크

-0.45

mphony

-0.45

POSITIVE LOGITS

 utafitiHapana

0.79

StoryboardSegue

0.68

Personendaten

0.63

__(/*!

0.60

 تضيفلها

0.59

verwijspagina

0.59

ContentLoaded

0.59

Ohhhh

0.59

tonode

0.56

 referenties

0.56

Activations Density 0.075%

exclamatory phrases expressing surprise or emphasis

No Comments

No Known Activations