INDEX

Explanations

proper nouns related to geographic locations, specific places, or interests in articles

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

 CreateTagHelper

-0.52

ieli

-0.50

Tube

-0.50

Öl

-0.50

CrossRef

-0.49

 autorytatywna

-0.49

 Thin

-0.48

 nakalista

-0.48

odeon

-0.47

AspNetCore

-0.47

POSITIVE LOGITS

webElementXpaths

0.73

__":

0.72

دانشنامهٔ

0.71

 Normdatei

0.70

 Chesterfield

0.68

 Leicestershire

0.67

initComponents

0.67

__':

0.66

feinander

0.65

HasAnnotation

0.65

Activations Density 0.918%

proper nouns related to geographic locations, specific places, or interests in articles

No Comments

No Known Activations