INDEX

Explanations

special formatting or structure within text, likely indicating section breaks or organizational elements

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

FieldBuilder

-0.43

matchCondition

-0.32

AccessorTable

-0.32

 שוליים

-0.30

PyExc

-0.30

 "..\..\

-0.30

 عرض

-0.29

coher

-0.29

See

-0.28

ricas

-0.28

POSITIVE LOGITS

 المعيارى

0.59

 motivación

0.53

TOBER

0.52

 kasarigan

0.52

 Paglinawan

0.52

 zoude

0.52

importer

0.49

UpInside

0.49

ReusableCell

0.49

MessageState

0.48

Activations Density 0.000%

special formatting or structure within text, likely indicating section breaks or organizational elements

No Comments

No Known Activations