INDEX

Explanations

markers and references commonly used in academic writing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.58

IFORNIA

-0.56

—

-0.51

ISODE

-0.51

djangoproject

-0.50

</caption>

-0.49

-0.48

ssaint

-0.48

ratulations

-0.47

stretchr

-0.47

POSITIVE LOGITS

ISupport

0.84

 meriva

0.81

 ainfi

0.79

+:+

0.78

 becauſe

0.77

 ſever

0.72

 zijne

0.71

 saveiro

0.71

 anún

0.71

 Shakspeare

0.70

Activations Density 3.302%

markers and references commonly used in academic writing

No Comments

No Known Activations