INDEX

Explanations

references to specific individuals or names in various contexts

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

 müßte

-0.95

 daß

-0.95



-0.95

 jScrollPane

-0.95

出版年

-0.93

 kasarigan

-0.91

 Мексичка

-0.88

 pinulongan

-0.87

 muß

-0.86

 ninh

-0.85

POSITIVE LOGITS

 Instagram

0.86

 https

0.73

https

0.72

 microbiome

0.68

 selfies

0.68

 TikTok

0.67

 selfie

0.67

Instagram

0.66

 github

0.63

AspNetCore

0.60

Activations Density 1.487%

references to specific individuals or names in various contexts

No Comments

No Known Activations