INDEX

Explanations

references to specific entities or classifications, particularly denoted by 'E' followed by a number

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

IntoConstraints

-0.66

 فريبيس

-0.62

willReturn

-0.52

 Grunde

-0.50

prepareStatement

-0.50

StoryboardSegue

-0.50

tableFuture

-0.49

 Соб

-0.48

 generale

-0.48

AccessFile

-0.47

POSITIVE LOGITS

glise

0.51

vident

0.51

Bronnen

0.49

arning

0.48

rawDesc

0.48

clectic

0.48

tymologie

0.47

 estimés

0.47

difice

0.44

gitto

0.44

Activations Density 0.221%

references to specific entities or classifications, particularly denoted by 'E' followed by a number

No Comments

No Known Activations