INDEX

Explanations

sections related to scientific analysis or methodology

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

 вікі

-0.68

 mukana

-0.65

IonicModule

-0.65

€”

-0.64

>>()

-0.63

 Vang

-0.61

 betweenstory

-0.61

 saites

-0.61

"]];

-0.61

 متعلقه

-0.61

POSITIVE LOGITS

AutoSize

4.90

labelControl

1.30

 NgModule

0.72

 CreateTagHelper

0.70

prepareStatement

0.65

complexType

0.64

GeneratedValue

0.63

AutoScale

0.59

 rowspan

0.59

simpleType

0.59

Activations Density 0.005%

sections related to scientific analysis or methodology

No Comments

No Known Activations