INDEX

Explanations

references to functions or methods associated with programming or technical documentation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.hook_resid_post

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

ArgsConstructor

-0.59

 Roskov

-0.53

styleType

-0.51

 protoimpl

-0.50

MockBean

-0.50

httphttps

-0.50

MessageOf

-0.48

咖

-0.47

цезда

-0.47

SLP

-0.46

POSITIVE LOGITS

awtextra

0.52

 disambiguazione

0.43

 kyse

0.40

 tangki

0.39

 polizia

0.37

 Jefus

0.36

 humanidade

0.36

 paisagem

0.36

 puertas

0.35

 skupina

0.35

Activations Density 0.017%

references to functions or methods associated with programming or technical documentation

No Comments

No Known Activations