INDEX

Explanations

non-standard punctuation marks or formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

rama

-0.49

 veter

-0.49

nor

-0.48

 hope

-0.47

antMatchers

-0.47

 convi

-0.47

 ural

-0.46

Gu

-0.46

Показать

-0.43

aggi

-0.42

POSITIVE LOGITS

 fathoms

0.76

 itſelf

0.75

dafx

0.74

 GIPHY

0.73

 Spisak

0.72

 ComVisible

0.70

 Numerade

0.70

 parson

0.69

verwijspagina

0.68

 Babyl

0.67

Activations Density 0.254%

non-standard punctuation marks or formatting elements

No Comments

No Known Activations