INDEX

Explanations

references to specific medical conditions or health-related terms

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

C macro definitions

np_acts-logits-general · gemini-2.0-flash

programming identifiers or code keywords

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.79

-0.73

-0.71

-0.70

-0.68

-0.67

POSITIVE LOGITS

 itſelf

1.81

 myſelf

1.80

ſelf

1.74

 Shakspeare

1.64

 ་་

1.62

ſelves

1.60

 iſt

1.59

 Jefus

1.57

 Monfieur

1.53

 Houſe

1.52

Activations Density 0.579%

references to specific medical conditions or health-related terms

C macro definitions

programming identifiers or code keywords

No Comments

No Known Activations