INDEX

Explanations

technical terms and components related to programming and software development

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

tagext

-0.67

TagHelpers

-0.66

 InputDecoration

-0.63

 AdapterView

-0.62

 AttributeSet

-0.58

 صوتيه

-0.55

πάρχ

-0.54

NUMX

-0.53

 nahilalakip

-0.53

PageContext

-0.52

POSITIVE LOGITS

 workaround

1.09

 troubleshooting

0.99

 troubleshoot

0.91

 solution

0.83

 solved

0.81

 solve

0.78

 problem

0.78

解決

0.77

 reproducible

0.75

Solution

0.74

Activations Density 0.942%

technical terms and components related to programming and software development

No Comments

No Known Activations