INDEX

Explanations

special characters and notations specific to structured formats or data entries

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

 propOrder

-0.94

Kanye

-0.80

 Stiles

-0.75

 Вікі

-0.74

 Magnolia

-0.71

 Magno

-0.71

 trebui

-0.71

⠀

-0.70

ngths

-0.70

 viewType

-0.69

POSITIVE LOGITS

RegressionTest

0.89

Dot

0.85

dot

0.83

 Strick

0.83

 parson

0.82

 Moles

0.80

Kuz

0.78

 patches

0.77

Rub

0.75

 hacks

0.75

Activations Density 0.538%

special characters and notations specific to structured formats or data entries

No Comments

No Known Activations