INDEX

Explanations

mentions of the name "Norman."

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

 Norman

-2.27

Norman

-2.16

 NORMAN

-1.82

 norman

-1.65

 Norm

-1.18

Norm

-1.12

norm

-1.02

 norm

-0.99

Нор

-0.93

 Нор

-0.90

POSITIVE LOGITS

 createSprite

0.48

漂

0.45

 Neutr

0.43

MeasureSpec

0.43

 Cougars

0.42

 nahilalakip

0.42

TestingModule

0.42

 gevo

0.41

quelize

0.41

eof

0.41

Activations Density 0.001%

mentions of the name "Norman."

No Comments

No Known Activations