INDEX

Explanations

references to various types of content, including articles, products, and user interactions

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

httphttps

-0.58

новниш

-0.57

DoubleQuotes

-0.57

."),

-0.54

 BoxFit

-0.52

 protoimpl

-0.52

Демографія

-0.51

]))

-0.49

 marquées

-0.48

Jeografia

-0.48

POSITIVE LOGITS

 Details

0.77

 details

0.72

 number

0.62

 name

0.61

 Name

0.61

 Info

0.59

 Provided

0.57

 summary

0.57

 link

0.57

 DETAILS

0.56

Activations Density 0.479%

references to various types of content, including articles, products, and user interactions

No Comments

No Known Activations