INDEX

Explanations

words related to inquiries or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

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

DockStyle

-0.84

WebElementEntity

-0.80



-0.76

GEBURTSDATUM

-0.75

 MainAxisSize

-0.74

 ContentValues

-0.71

 WaitForSeconds

-0.70

("]");

-0.69

IntoConstraints

-0.68

}{@

-0.67

POSITIVE LOGITS

GRACIAS

0.55

tinyos

0.52

성

0.52

 Thank

0.51

THANK

0.49

ERA

0.47

 Einf

0.47

 thank

0.45

oficina

0.45

 organelles

0.45

Activations Density 0.033%

words related to inquiries or questions

No Comments

No Known Activations