INDEX

Explanations

phrases related to the importance and evaluation of concepts or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Wicidata

-0.80

Portail

-0.69

EndContext

-0.67

клопе

-0.59

soort

-0.57

 AssemblyCulture

-0.53

CrossRef

-0.52

AndEndTag

-0.52

нциклопедия

-0.51

 intStringLen

-0.50

POSITIVE LOGITS

ValueStyle

0.64

 NSCoder

0.58

EditorBrowsable

0.57

SpringBootTest

0.57

UnsafeEnabled

0.53

 counted

0.52

허

0.52

 commented

0.49

Билгалдахарш

0.48

ണ്

0.48

Activations Density 0.987%

phrases related to the importance and evaluation of concepts or entities

No Comments

No Known Activations