INDEX

Explanations

content related to templates, documents, or organizational structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"Template" or thanks related text

np_acts-logits-general · gemini-2.0-flash

template cv

np_acts-logits-general · gemini-2.5-flash-lite

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

 OFDb

-0.76

Portály

-0.72

BufferException

-0.68

ThroughAttribute

-0.67

 '\\;'

-0.67

rrggbb

-0.63

 surla

-0.61

Portail

-0.61

useNewUrlParser

-0.60

 AssemblyProduct

-0.58

POSITIVE LOGITS

 template

2.44

 templates

2.26

 Template

2.01

template

1.99

 Templates

1.89

Template

1.87

模板

1.76

 TEMPLATE

1.72

templates

1.70

TEMPLATE

1.66

Activations Density 0.395%

content related to templates, documents, or organizational structures

"Template" or thanks related text

template cv

No Comments

No Known Activations