INDEX

Explanations

references to entities within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-0.99

 Monfieur

-0.98

 pleaſure

-0.96

 Theſe

-0.88

UserScript

-0.88

 houſe

-0.81

 Majefty

-0.81

 Jefus

-0.81

 purpoſe

-0.80

 reaſon

-0.80

POSITIVE LOGITS

 entity

0.88

entity

0.81

ENTITY

0.71

rid

0.68

 ENTITY

0.59

 entidad

0.57

 entities

0.54

 aside

0.53

ப்பட்டது

0.50

 said

0.49

Activations Density 0.091%

references to entities within the text

No Comments

No Known Activations