INDEX

Explanations

phrases expressing preference or desire

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

SizeF

-0.87

LookAnd

-0.76

NamedQueries

-0.75

XmlAccessType

-0.61

tagHelperRunner

-0.60

__(/*!

-0.60

KURZBESCHREIBUNG

-0.60

 transfieras

-0.58

}:

-0.58

SOUNDBITE

-0.57

POSITIVE LOGITS

 want

1.07

wants

1.07

 wants

1.01

want

0.95

 Want

0.94

 gustaría

0.90

 wish

0.89

 Wants

0.88

WANT

0.87

 wishes

0.85

Activations Density 0.110%

phrases expressing preference or desire

No Comments

No Known Activations