INDEX

Explanations

phrases that indicate actions or necessities related to outcomes or goals

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

 suprême

-0.57

 cero

-0.55

டுத்த

-0.55

 demands

-0.53

IMENT

-0.53

CHELL

-0.52

 bulat

-0.52

 Dickson

-0.52

schrift

-0.51

oob

-0.51

POSITIVE LOGITS

onOptions

0.79

Geographie

0.74

 Cæsar

0.74

 myſelf

0.73

 المعيارى

0.71

Efq

0.70

XmlRootElement

0.68

 insuffisamment

0.67

 himſelf

0.65

 IBOutlet

0.65

Activations Density 0.217%

phrases that indicate actions or necessities related to outcomes or goals

No Comments

No Known Activations