INDEX

Explanations

expressions of negation and emphasis related to quantities or absolutes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

op

-0.51

tez

-0.50

 riusc

-0.50

zir

-0.49

ile

-0.48

 bonté

-0.47

 riuscito

-0.47

hez

-0.47

rach

-0.46

 Exactly

-0.46

POSITIVE LOGITS

audiovisuel

0.68

OCCURRED

0.67

PhysRevLett

0.66

menopausal

0.65

 disponibilités

0.64

ConstraintMaker

0.64

 Lijst

0.63

kmäler

0.62

UserScript

0.62

WebVitals

0.60

Activations Density 0.525%

expressions of negation and emphasis related to quantities or absolutes

No Comments

No Known Activations