INDEX

Explanations

names of individuals or families

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

 للمعارف

-0.70

IsMutable

-0.68

SharedDtor

-0.59

 CURIAM

-0.59

"])

-0.57

igraphy

-0.56

COMES

-0.56

pecting

-0.55

MemoryWarning

-0.54

mido

-0.54

POSITIVE LOGITS

তথ্যসূত্র

0.50

 vectorielle

0.50

antd

0.48

tagext

0.47

 Valer

0.46

 Pseudo

0.45

IntoConstraints

0.45

 Phuket

0.45

годні

0.44

Jr

0.43

Activations Density 0.001%

names of individuals or families

No Comments

No Known Activations