INDEX

Explanations

programming constructs and property definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ſche

-0.85

 Monfieur

-0.82

Rüyada

-0.76

 Meksiku

-0.76

 myſelf

-0.76

 againſt

-0.71

 Majefty

-0.69

 iſt

-0.68

 Theſe

-0.68

Efq

-0.65

POSITIVE LOGITS

 real

0.55

ürlich

0.50

 reales

0.50

 viewDidLoad

0.50

itattu

0.49

日閲覧

0.49

 known

0.49

 Wicidata

0.48

diğini

0.47

httphttps

0.47

Activations Density 0.038%

programming constructs and property definitions

No Comments

No Known Activations