INDEX

Explanations

terms and phrases that indicate significant contrasts or differences between concepts, particularly in social or political contexts

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ercicio

-0.45

RTLU

-0.45

EDEFAULT

-0.44

AddTagHelper

-0.44

issements

-0.44

NOPQRST

-0.42

batim

-0.42

featureID

-0.42

 kuten

-0.42

ísimo

-0.42

POSITIVE LOGITS

+#+

0.57

rungsseite

0.56

ValueStyle

0.53

 utafitiHapana

0.50

 للمعارف

0.43

曖昧さ回避

0.42

EndInit

0.42

 demonstrate

0.41

jspb

0.39

EndProject

0.36

Activations Density 0.066%

terms and phrases that indicate significant contrasts or differences between concepts, particularly in social or political contexts

No Comments

No Known Activations