INDEX

Explanations

geographical locations and names associated with specific places

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

 ſet

-0.55

 pleaſure

-0.55

 Приступљено

-0.52

 consultato

-0.49

 RoutedEventArgs

-0.48

SpringBootTest

-0.47

pulseira

-0.47

 tranſ

-0.47

 Reſ

-0.47

ValueStyle

-0.47

POSITIVE LOGITS

 меж

0.36

 Interact

0.35

bebasan

0.35

 Đó

0.35

ervos

0.35

pao

0.35

 Händen

0.34

ArrowToggle

0.34

tare

0.34

 Alas

0.34

Activations Density 0.107%

geographical locations and names associated with specific places

No Comments

No Known Activations