INDEX

Explanations

categories and classifications related to individuals or entities

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

fauteuil

-0.44

 Spisak

-0.43

 argint

-0.42

 podjet

-0.40

acamata

-0.40

ValueStyle

-0.39

 oamen

-0.38

IsContent

-0.38

ñador

-0.38

 gafas

-0.37

POSITIVE LOGITS

 CanadaChoose

0.54

webElementXpaths

0.50

TypedDataSet

0.48

 dAtA

0.47

writeFieldEnd

0.45

LEGGI

0.44

Tembelea

0.44

nemies

0.43

upol

0.42

<!--[

0.41

Activations Density 0.001%

categories and classifications related to individuals or entities

No Comments

No Known Activations