INDEX

Explanations

scientific terms related to experimental controls and variables

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

a control group

np_acts-logits-general · gemini-2.0-flash

control and baseline groups

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 ujednoznacz

-0.71

 >=",

-0.53

TargetException

-0.51

 persönlich

-0.51

EndProject

-0.50

 calendriers

-0.50

 EClass

-0.49

rungsseite

-0.49

 الرياضيه

-0.49

::::::::

-0.48

POSITIVE LOGITS

 baseline

1.00

baseline

0.79

Baseline

0.76

 benchmark

0.71

 Baseline

0.71

 normaux

0.67

 témoins

0.67

 normal

0.67

 unmodified

0.66

 normalen

0.65

Activations Density 1.610%

scientific terms related to experimental controls and variables

a control group

control and baseline groups

No Comments

No Known Activations