INDEX

Explanations

phrases indicating additional information or supplementary content

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

قایناقلار

-0.69

 Photocase

-0.67

HtmlAttribute

-0.64

 wikipagina

-0.63

Искәрмәләр

-0.62

feinander

-0.61

 carmen

-0.61

 المثال

-0.59



-0.59

TouchListener

-0.59

POSITIVE LOGITS

 besides

0.94

besides

0.87

Besides

0.83

 Besides

0.82

 Além

0.77

 Oltre

0.77

 Außer

0.76

enumi

0.76

Além

0.70

mybatisplus

0.66

Activations Density 0.094%

phrases indicating additional information or supplementary content

No Comments

No Known Activations