INDEX

Explanations

names and titles related to historical figures and events

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

ValueStyle

-0.45

uș

-0.36

AutoScaleMode

-0.32

 palanca

-0.31

 cheiro

-0.30

 quæ

-0.28

atisfaction

-0.28

 autores

-0.28

AutoModerator

-0.27

 rost

-0.27

POSITIVE LOGITS

IsMutable

0.60

Rüyada

0.57

ngdoc

0.55

ContentAsync

0.55

Spoljašnje

0.53

webElementXpaths

0.51

MessageTagHelper

0.51



0.50

vician

0.50

 EconPapers

0.50

Activations Density 0.147%

names and titles related to historical figures and events

No Comments

No Known Activations