INDEX

Explanations

terms related to data integrity and emotional responses

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

resentment and digest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 /\.(

-0.88

VersionUID

-0.86

 Borel

-0.81

-0.79

createServer

-0.77

 Blackwell

-0.76

GoogleApiClient

-0.76

cdnjs

-0.73

].)

-0.73

AddHtmlAttribute

-0.71

POSITIVE LOGITS

dto

1.18

dto

1.13

Dto

1.06

Dtos

0.91

nestjs

0.73

 Rossetti

0.72

DTO

0.68

Abp

0.68

DTO

0.68

DTOs

0.67

Activations Density 0.007%

terms related to data integrity and emotional responses

resentment and digest

No Comments

No Known Activations