INDEX

Explanations

references to entrances and entrances-related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 autorytatywna

-0.81

出版年

-0.78

 يتيمه

-0.76

ритори

-0.76

aarrggbb

-0.72

 transférez

-0.71

MigrationBuilder

-0.71

 transfieras

-0.68

ReusableCell

-0.67

GEBURTSDATUM

-0.67

POSITIVE LOGITS

 entrance

0.98

 Entrance

0.86

 entry

0.86

Entrance

0.79

 stairs

0.78

 gate

0.76

 stairway

0.74

 entrances

0.74

 Eingang

0.73

 Entry

0.73

Activations Density 0.132%

references to entrances and entrances-related phrases

No Comments

No Known Activations