INDEX

Explanations

citations and references in academic texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 tän

-0.60

 {}'.

-0.55

foc

-0.54

 relev

-0.54

 👉

-0.54

 incentiv

-0.53

 déplo

-0.52

 features

-0.51

 impactful

-0.50

'])->

-0.50

POSITIVE LOGITS

 mußte

0.75

 müßte

0.73

 nạ

0.72

出版年

0.67

 mußten

0.66

 muß

0.66

XmlAccessType

0.66

енча

0.66

 AssemblyVersion

0.66

luß

0.66

Activations Density 0.065%

citations and references in academic texts

No Comments

No Known Activations