INDEX

Explanations

references to experiments and experimental protocols

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

the word "experiment" or "experiments."

np_acts-logits-general · gemini-2.0-flash

scientific experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ếng

-0.61

Submissions

-0.59

getline

-0.57

saraba

-0.56

 kän

-0.56

KEYCODE

-0.56

submissions

-0.56

 iceberg

-0.55

 professionali

-0.55

binaan

-0.55

POSITIVE LOGITS

 experiment

2.46

 experiments

2.35

 Experiment

2.11

experiment

2.01

 Experiments

1.97

Experiment

1.94

 experimento

1.86

experiments

1.84

Experiments

1.81

 EXPERIMENT

1.78

Activations Density 0.680%

references to experiments and experimental protocols

the word "experiment" or "experiments."

scientific experiments

No Comments

No Known Activations