INDEX

Explanations

terms related to treatment comparisons and experimental group distinctions

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

a control group

np_acts-logits-general · gemini-2.0-flash

control group comparison

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

createClass

-0.63

prefixer

-0.61

الحياه

-0.56

 ujednoznacz

-0.55

луй

-0.53

 kasarigan

-0.52

 CanadaChoose

-0.51

IBC

-0.50

 <<<<<<<<<<<<<<

-0.50

 Feminine

-0.50

POSITIVE LOGITS

 control

2.19

 Control

1.93

control

1.89

 controls

1.85

Control

1.78

 CONTROL

1.75

 Controls

1.64

CONTROL

1.64

controls

1.52

 controles

1.49

Activations Density 1.977%

terms related to treatment comparisons and experimental group distinctions

a control group

control group comparison

No Comments

No Known Activations