INDEX

Explanations

mathematical notation and expressions related to calculus or algebra

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

-0.52

بری

-0.48

 grote

-0.42

Zdroj

-0.42

dbg

-0.42

 great

-0.42

 beant

-0.41

…

-0.41

奏

-0.41

<eos>

-0.41

POSITIVE LOGITS

tvguidetime

0.94

 насељу

0.89

 المعيارى

0.87

 Chriftian

0.86

 AssemblyTitle

0.83

sidemargin

0.82

 ErrIntOverflow

0.82

 AppBundle

0.78

messageInfo

0.77

 myſelf

0.77

Activations Density 5.612%

mathematical notation and expressions related to calculus or algebra

No Comments

No Known Activations