INDEX

Explanations

phrases related to design and purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AndEndTag

-0.83

 يتيمه

-0.80

 EconPapers

-0.73

ⓧ

-0.73

 كومونز

-0.72

titleMargin

-0.70

 Dernière

-0.65

üyor

-0.63

aarrggbb

-0.62

WEBPACK

-0.60

POSITIVE LOGITS

 designed

0.99

 intended

0.88

designed

0.84

Intended

0.80

intended

0.79

 meant

0.76

 Designed

0.76

 purpose

0.74

Designed

0.73

 destinés

0.73

Activations Density 0.188%

phrases related to design and purpose

No Comments

No Known Activations