INDEX

Explanations

references to significant events or milestones in history

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

Dates with the year 200_

np_acts-logits-general · gemini-2.0-flash

dates and years

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

InjectAttribute

-0.86

SuppressMessage

-0.77

 وتسجيلات

-0.76

/**

-0.68

)|^{

-0.63

[]:

-0.61

laquo

-0.61

 WaitForSeconds

-0.59

GeneratedCode

-0.59

ApiProperty

-0.59

POSITIVE LOGITS

0.73

0.70

0.67

0.65

0.63

0.62

RenderAtEndOf

0.62

0.60

 Obrador

0.60

bollah

0.60

Activations Density 0.112%

references to significant events or milestones in history

Dates with the year 200_

dates and years

No Comments

No Known Activations