INDEX

Explanations

occurrences of the prefix "en"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

en

-1.71

En

-0.93

En

-0.86

EN

-0.77

eno

-0.60

 <>",

-0.59

 jspb

-0.51

enz

-0.51

UnitTesting

-0.50

 ench

-0.50

POSITIVE LOGITS

RectangleBorder

0.45

metingen

0.44

 Ahnung

0.43

 Italijanski

0.41

mobileqq

0.40

ruik

0.39

 ujedno

0.38

 invokingState

0.37

 Superhost

0.37

ffles

0.37

Activations Density 0.002%

occurrences of the prefix "en"

No Comments

No Known Activations